Distr-class: Class 'Distr'

Description

R6 Class for Distribution Objects

Public fields

Methods

Public methods

• Distr$new()

• Distr$plot()

• Distr$clone()

Method new()

Initialize the fiels of the 'Distribution' object

Usage

Distr$new(x, name, parameters, sd, n, loglik)

Arguments

Method plot()

Plot the distribution with histogram and fitted density curve.

Usage

Distr$plot(
  main = NULL,
  xlab = NULL,
  xlim = NULL,
  xlim.t = TRUE,
  ylab = NULL,
  line.col = "red",
  fill.col = "lightblue",
  border.col = "black",
  box = TRUE,
  line.width = 1
)

Arguments

Method clone()

The objects of this class are cloneable with this method.

Usage

Distr$clone(deep = FALSE)

Arguments

See Also

distribution, FitDistr, DistrCollection

Examples

# Normal
set.seed(123)
data1 <- rnorm(100, mean = 5, sd = 2)
parameters1 <- list(mean = 5, sd = 2)
distr1 <- Distr$new(x = data1, name = "normal", parameters = parameters1,
                    sd = 2, n = 100, loglik = -120)
distr1$plot()

# Log-normal
data2 <- rlnorm(100, meanlog = 1, sdlog = 0.5)
parameters2 <- list(meanlog = 1, sdlog = 0.5)
distr2 <- Distr$new(x = data2, name = "log-normal", parameters = parameters2,
                    sd = 0.5, n = 100, loglik = -150)
distr2$plot()

# Geometric
data3 <- rgeom(100, prob = 0.3)
parameters3 <- list(prob = 0.3)
distr3 <- Distr$new(x = data3, name = "geometric", parameters = parameters3,
                    sd = sqrt((1 - 0.3) / (0.3^2)), n = 100, loglik = -80)
distr3$plot()

# Exponential
data4 <- rexp(100, rate = 0.2)
parameters4 <- list(rate = 0.2)
distr4 <- Distr$new(x = data4, name = "exponential", parameters = parameters4,
                    sd = 1 / 0.2, n = 100, loglik = -110)
distr4$plot()

# Poisson
data5 <- rpois(100, lambda = 3)
parameters5 <- list(lambda = 3)
distr5 <- Distr$new(x = data5, name = "poisson", parameters = parameters5,
                    sd = sqrt(3), n = 100, loglik = -150)
distr5$plot()

# Chi-square
data6 <- rchisq(100, df = 5)
parameters6 <- list(df = 5)
distr6 <- Distr$new(x = data6, name = "chi-squared", parameters = parameters6,
                    sd = sqrt(2 * 5), n = 100, loglik = -130)
distr6$plot()

# Logistic
data7 <- rlogis(100, location = 0, scale = 1)
parameters7 <- list(location = 0, scale = 1)
distr7 <- Distr$new(x = data7, name = "logistic", parameters = parameters7,
                    sd = 1 * sqrt(pi^2 / 3), n = 100, loglik = -140)
distr7$plot()

# Gamma
data8 <- rgamma(100, shape = 2, rate = 0.5)
parameters8 <- list(shape = 2, rate = 0.5)
distr8 <- Distr$new(x = data8, name = "gamma", parameters = parameters8,
                    sd = sqrt(2 / (0.5^2)), n = 100, loglik = -120)
distr8$plot()

# f
data9 <- rf(100, df1 = 5, df2 = 10)
parameters9 <- list(df1 = 5, df2 = 10)
df1 <- 5
df2 <- 10
distr9 <- Distr$new(x = data9, name = "f", parameters = parameters9,
                    sd = sqrt(((df2^2 * (df1 + df2 - 2)) /
                               (df1 * (df2 - 2)^2 * (df2 - 4)))),
                    n = 100, loglik = -150)
distr9$plot()

# t
data10 <- rt(100, df = 10)
parameters10 <- list(df = 10)
distr10 <- Distr$new(x = data10, name = "t", parameters = parameters10,
                     sd = sqrt(10 / (10 - 2)), n = 100, loglik = -120)
distr10$plot()

# negative binomial
data11 <- rnbinom(100, size = 5, prob = 0.3)
parameters11 <- list(size = 5, prob = 0.3)
distr11 <- Distr$new(x = data11, name = "negative binomial",
                     parameters = parameters11,
                     sd = sqrt(5 * (1 - 0.3) / (0.3^2)),
                     n = 100, loglik = -130)
distr11$plot()

DistrCollection-class: Class 'DistrCollection'

Description

R6 Class for Managing a Collection of Distribution Objects

Public fields

Methods

Public methods

• DistrCollection$new()

• DistrCollection$add()

• DistrCollection$get()

• DistrCollection$print()

• DistrCollection$summary()

• DistrCollection$plot()

• DistrCollection$clone()

Method new()

Initialize the fields of the DistrCollection object.

Usage

DistrCollection$new()

Method add()

Add a Distr object to the collection.

Usage

DistrCollection$add(distr)

Arguments

Method get()

Get a Distr object from the collection by its index.

Usage

DistrCollection$get(i)

Arguments

Returns

A Distr object.

Method print()

Print the summary of all distributions in the collection.

Usage

DistrCollection$print()

Method summary()

Summarize the goodness of fit for all distributions in the collection.

Usage

DistrCollection$summary()

Returns

A data frame with distribution names, Anderson-Darling test statistics, and p-values.

Method plot()

Plot all distributions in the collection.

Usage

DistrCollection$plot(
  xlab = NULL,
  ylab = NULL,
  xlim = NULL,
  ylim = NULL,
  line.col = "red",
  fill.col = "lightblue",
  border.col = "black",
  line.width = 1,
  box = TRUE
)

Arguments

Method clone()

The objects of this class are cloneable with this method.

Usage

DistrCollection$clone(deep = FALSE)

Arguments

See Also

Distr, distribution, FitDistr

Examples

set.seed(123)
data1 <- rnorm(100, mean = 5, sd = 2)
parameters1 <- list(mean = 5, sd = 2)
distr1 <- Distr$new(x = data1, name = "normal",
                    parameters = parameters1, sd = 2,
                    n = 100, loglik = -120)

data2 <- rpois(100, lambda = 3)
parameters2 <- list(lambda = 3)
distr2 <- Distr$new(x = data2, name = "poisson",
                    parameters = parameters2, sd = sqrt(3),
                    n = 100, loglik = -150)
collection <- DistrCollection$new()
collection$add(distr1)
collection$add(distr2)
collection$summary()
collection$plot()

FitDistr: Maximum-likelihood Fitting of Univariate Distributions

Description

Maximum-likelihood fitting of univariate distributions, allowing parameters to be held fixed if desired.

Usage

FitDistr(x, densfun, start, ...)

Arguments

Details

For the Normal, log-Normal, geometric, exponential and Poisson distributions the closed-form MLEs (and exact standard errors) are used, and 'start' should not be supplied.

For all other distributions, direct optimization of the log-likelihood is performed using 'optim'. The estimated standard errors are taken from the observed information matrix, calculated by a numerical approximation. For one-dimensional problems the Nelder-Mead method is used and for multi-dimensional problems the BFGS method, unless arguments named 'lower' or 'upper' are supplied (when 'L-BFGS-B' is used) or 'method' is supplied explicitly.

For the '"t"' named distribution the density is taken to be the location-scale family with location 'm' and scale 's'.

For the following named distributions, reasonable starting values will be computed if 'start' is omitted or only partially specified: '"cauchy"', '"gamma"', '"logistic"', '"negative binomial"' (parametrized by mu and size), '"t"' and '"weibull"'. Note that these starting values may not be good enough if the fit is poor: in particular they are not resistant to outliers unless the fitted distribution is long-tailed.

There are 'print', 'coef', 'vcov' and 'logLik' methods for class '"FitDistr"'.

Value

The function 'FitDistr' returns an object of class 'fitdistr', which is a list containing:

See Also

distribution, Distr, DistrCollection.

Examples

set.seed(123)
x = rgamma(100, shape = 5, rate = 0.1)
FitDistr(x, "gamma")

# Now do this directly with more control.
FitDistr(x, dgamma, list(shape = 1, rate = 0.1), lower = 0.001)

set.seed(123)
x2 = rt(250, df = 9)
FitDistr(x2, "t", df = 9)

# Allow df to vary: not a very good idea!
FitDistr(x2, "t")

# Now do fixed-df fit directly with more control.
mydt = function(x, m, s, df) dt((x-m)/s, df)/s
FitDistr(x2, mydt, list(m = 0, s = 1), df = 9, lower = c(-Inf, 0))

set.seed(123)
x3 = rweibull(100, shape = 4, scale = 100)
FitDistr(x3, "weibull")

MSALinearity-class: Class 'MSALinearity'

Description

R6 class for performing Measurement System Analysis (MSA) Linearity studies.

Public fields

Methods

Public methods

• MSALinearity$response()

• MSALinearity$summary()

• MSALinearity$plot()

• MSALinearity$print()

• MSALinearity$as.data.frame()

• MSALinearity$clone()

Method response()

Get and set the the response in an object of class MSALinearity.

Usage

MSALinearity$response(value)

Arguments

Method summary()

Methods for function summary in Package base.

Usage

MSALinearity$summary()

Method plot()

Plots the measurement system, including individual biases, mean bias, and a regression line with confidence intervals.

Usage

MSALinearity$plot(ylim, col, pch, lty = c(1, 2))

Arguments

Method print()

Methods for function print in Package base.

Usage

MSALinearity$print()

Method as.data.frame()

Return a data frame with the information of the object MSALinearity.

Usage

MSALinearity$as.data.frame()

Method clone()

The objects of this class are cloneable with this method.

Usage

MSALinearity$clone(deep = FALSE)

Arguments

adSim: Bootstrap-based Anderson-Darling Test for Univariate

Description

Performs the Anderson-Darling test for univariate distributions with an option for bootstrap-based p-value determination. It also allows p-value determination using tabled critical values.

Usage

adSim(x, distribution = "normal", b = 10000)

Arguments

Details

The function first estimates the parameters for the tested distribution, typically using Maximum-Likelihood Estimation (MLE) via the FitDistr function. For normal and log-normal distributions, parameters are estimated by the mean and standard deviation. Cauchy distribution parameters are fitted by the sums of the weighted order statistic when using tabled critical values. The Anderson-Darling statistic is then calculated based on these estimated parameters.

Parametric bootstrapping generates the distribution of the Anderson-Darling test statistic, which is used to determine the p-value. This simulation-based Anderson-Darling distribution and its corresponding critical values for selected quantiles can be printed. If simulation is not performed, a p-value is obtained from tabled critical values, although no exact expressions exist except for the log-normal, normal, and exponential distributions.

Value

A list containing the following components:

distribution

The distribution for which the Anderson-Darling test was applied.

parameter_estimation

The estimated parameters for the distribution.

Anderson_Darling

The value of the Anderson-Darling test statistic.

p_value

The corresponding p-value, either simulated or from tabled values.

critical_values

The critical values corresponding to the 0.75, 0.90, 0.95, 0.975, and 0.99 quantiles, either simulated or from tables.

simAD

The bootstrap-based Anderson-Darling distribution.

Examples

x <- rnorm(25, 32, 2)
adSim(x)
adSim(x, "logistic", 2000)
adSim(x, "cauchy", NA)
adSim(x, "exponential", 2000)
adSim(x, "gumbel", 2000)

aliasTable: Display an alias table

Description

This function generates an alias table for a factorial design object.

Usage

aliasTable(fdo, degree, print = TRUE)

Arguments

Value

The function aliasTable returns a matrix indicating the aliased effects.

See Also

fracDesign, fracChoose

Examples

# Create a fractional factorial design
dfrac <- fracDesign(k = 3, gen = "C = AB")
# Display the alias table for the fractional factorial design
aliasTable(dfrac)

as.data.frame_facDesign: Coerce to a data.frame

Description

Converts an object of class facDesign.c into a data frame.

Usage

as.data.frame_facDesign(dfac)

Arguments

Value

The function as.data.frame_facDesign returns a data frame.

Examples

fdo <- fracDesign(k = 2, replicates = 3, centerCube = 4)
as.data.frame_facDesign(fdo)

blocking: Blocking

Description

Blocks a given factorial or response surface design.

Usage

blocking(fdo, blocks, random.seed, useTable = "rsm", gen)

Arguments

Value

The function blocking returns an object of class facDesign.c with blocking structure.

See Also

facDesign.

Examples

# Example 1
#Create a 2^3 full factorial design
fdo <- facDesign(k = 3)
# Apply blocking to the design with 2 blocks
blocking(fdo, 2)

# Example 2
#Create a response surface design for 3 factors
fdo <- rsmDesign(k = 3)
# Apply blocking to the design with 3 blocks (1 block for star part and 2 blocks for the cube part)
blocking(fdo, 3)

cg: Function to calculate and visualize the gage capability.

Description

Function visualize the given values of measurement in a run chart and in a histogram. Furthermore the centralized Gage potential index Cg and the non-centralized Gage Capability index Cgk are calculated and displayed.

Usage

cg(
  x,
  target,
  tolerance,
  ref.interval,
  facCg,
  facCgk,
  n = 0.2,
  col,
  pch,
  xlim,
  ylim,
  conf.level = 0.95
)

Arguments

Details

The calculation of the potential and actual gage capability are based on the following formula:

• Cg = (facCg * tolerance[2]-tolerance[1])/ref.interval

• Cgk = (facCgk * abs(target-mean(x))/(ref.interval/2)

If the usage of the historical process variation is preferred the values for the tolerance tolerance must be adjusted manually. That means in case of the 6 sigma methodology for example, that tolerance = 6 * sigma[process].

Value

The function cg returns a list of numeric values. The first element contains the calculated centralized gage potential index Cg and the second contains the non-centralized gage capability index Cgk.

See Also

cg_RunChart, cg_HistChart, cg_ToleranceChart.

Examples

x <- c(9.991, 10.013, 10.001, 10.007, 10.010, 10.013, 10.008,9.992,
       10.017, 10.005, 10.005, 10.002, 10.017, 10.005, 10.002, 9.996,
       10.011, 10.009, 10.006, 10.008, 10.003, 10.002, 10.006, 10.010, 10.013)

cg(x = x, target = 10.003, tolerance = c(9.903, 10.103))

cg_HistChart

Description

Function visualize the given values of measurement in a histogram

Usage

cg_HistChart(
  x,
  target,
  tolerance,
  ref.interval,
  facCg,
  facCgk,
  n = 0.2,
  col,
  xlim,
  ylim,
  main,
  conf.level = 0.95,
  cgOut = TRUE
)

Arguments

Details

The calculation of the potential and actual gage capability are based on the following formulae:

• Cg = (facCg * tolerance[2]-tolerance[1])/ref.interval

• Cgk = (facCgk * abs(target-mean(x))/(ref.interval/2)

If the usage of the historical process variation is preferred the values for the tolerance tolerance must be adjusted manually. That means in case of the 6 sigma methodology for example, that tolerance = 6 * sigma[process].

Value

The function cg_HistChart returns a list of numeric values. The first element contains the calculated centralized gage potential index Cg and the second contains the non-centralized gage capability index Cgk.

See Also

cg_RunChart, cg_ToleranceChart, cg

Examples

x <- c(9.991, 10.013, 10.001, 10.007, 10.010, 10.013, 10.008,9.992,
       10.017, 10.005, 10.005, 10.002, 10.017, 10.005, 10.002, 9.996,
       10.011, 10.009, 10.006, 10.008, 10.003, 10.002, 10.006, 10.010, 10.013)

cg_HistChart(x = x, target = 10.003, tolerance = c(9.903, 10.103))

cg_RunChart

Description

Function visualize the given values of measurement in a Run Chart

Usage

cg_RunChart(
  x,
  target,
  tolerance,
  ref.interval,
  facCg,
  facCgk,
  n = 0.2,
  col = "black",
  pch = 19,
  xlim = NULL,
  ylim = NULL,
  main = "Run Chart",
  conf.level = 0.95,
  cgOut = TRUE
)

Arguments

Details

The calculation of the potential and actual gage capability are based on the following formulae:

• Cg = (facCg * tolerance[2]-tolerance[1])/ref.interval

• Cgk = (facCgk * abs(target-mean(x))/(ref.interval/2)

If the usage of the historical process variation is preferred the values for the tolerance tolerance must be adjusted manually. That means in case of the 6 sigma methodology for example, that tolerance = 6 * sigma[process].

Value

The function cg_RunChart returns a list of numeric values. The first element contains the calculated centralized gage potential index Cg and the second contains the non-centralized gage capability index Cgk.

See Also

cg_HistChart, cg_ToleranceChart, cg

Examples

x <- c(9.991, 10.013, 10.001, 10.007, 10.010, 10.013, 10.008,9.992,
       10.017, 10.005, 10.005, 10.002, 10.017, 10.005, 10.002, 9.996,
       10.011, 10.009, 10.006, 10.008, 10.003, 10.002, 10.006, 10.010, 10.013)

cg_RunChart(x = x, target = 10.003, tolerance = c(9.903, 10.103))

cg_ToleranceChart

Description

Function visualize the given values of measurement in a Tolerance View.

Usage

cg_ToleranceChart(
  x,
  target,
  tolerance,
  ref.interval,
  facCg,
  facCgk,
  n = 0.2,
  col,
  pch,
  xlim,
  ylim,
  main,
  conf.level = 0.95,
  cgOut = TRUE
)

Arguments

Details

The calculation of the potential and actual gage capability are based on the following formulae:

• Cg = (facCg * tolerance[2]-tolerance[1])/ref.interval

• Cgk = (facCgk * abs(target-mean(x))/(ref.interval/2)

If the usage of the historical process variation is preferred the values for the tolerance tolerance must be adjusted manually. That means in case of the 6 sigma methodology for example, that tolerance = 6 * sigma[process].

Value

The function cg_ToleranceChart returns a list of numeric values. The first element contains the calculated centralized gage potential index Cg and the second contains the non-centralized gage capability index Cgk.

See Also

cg_RunChart, cg_HistChart, cg

Examples

x <- c(9.991, 10.013, 10.001, 10.007, 10.010, 10.013, 10.008,9.992,
       10.017, 10.005, 10.005, 10.002, 10.017, 10.005, 10.002, 9.996,
       10.011, 10.009, 10.006, 10.008, 10.003, 10.002, 10.006, 10.010, 10.013)

cg_ToleranceChart(x = x, target = 10.003, tolerance = c(9.903, 10.103))

code2real: Coding

Description

Function to calculate the real value of a coded value.

Usage

code2real(low, high, codedValue)

Arguments

Value

The function return a real value of a coded value

Examples

code2real(160, 200, 0)

confounds: Confounded Effects

Description

Function to display confounded effects of a fractional factorial design in a human readable way.

Usage

confounds(x, depth = 2)

Arguments

Value

The function returns a summary of the factors confounded.

Examples

vp.frac = fracDesign(k = 4, gen = "D=ABC")
confounds(vp.frac,depth=5)

contourPlot: Contour Plot

Description

Creates a contour diagram for an object of class facDesign.c.

Usage

contourPlot(
  x,
  y,
  z,
  data = NULL,
  xlim,
  ylim,
  main,
  xlab,
  ylab,
  form = "fit",
  col = 1,
  steps,
  fun,
  plot = TRUE,
  show.scale = TRUE
)

Arguments

Value

The function contourPlot returns an invisible list containing:

• x - locations of grid lines for x at which the values in z are measured.

• y - locations of grid lines for y at which the values in z are measured.

• z - a matrix containing the values of z to be plotted.

• plot - The generated plot.

See Also

wirePlot, paretoChart

Examples

fdo = rsmDesign(k = 3, blocks = 2)
fdo$.response(data.frame(y = rnorm(fdo$nrow())))

#I - display linear fit
contourPlot(A,B,y, data = fdo, form = "linear")
#II - display full fit (i.e. effect, interactions and quadratic effects
contourPlot(A,B,y, data = fdo, form = "full")
#III - display a fit specified before
fdo$set.fits(fdo$lm(y ~ B + I(A^2)))
contourPlot(A,B,y, data = fdo, form = "fit")
#IV - display a fit given directly
contourPlot(A,B,y, data = fdo, form = "y ~ A*B + I(A^2)")
#V - display a fit using a different colorRamp
contourPlot(A,B,y, data = fdo, form = "full", col = 2)
#VI - display a fit using a self defined colorRamp
myColour = colorRampPalette(c("green", "gray","blue"))
contourPlot(A,B,y, data = fdo, form = "full", col = myColour)

contourPlot3: Ternary plot

Description

This function creates a ternary plot (contour plot) for mixture designs (i.e. object of class mixDesign).

Usage

contourPlot3(
  x,
  y,
  z,
  response,
  data = NULL,
  main,
  xlab,
  ylab,
  zlab,
  form = "linear",
  col = 1,
  col.text,
  axes = TRUE,
  steps,
  plot = TRUE,
  show.scale = TRUE
)

Arguments

Value

The function contourPlot3 returns an invisible list containing:

• mat - A matrix containing the response values as NA's and numerics.

• plot - The generated plot.

See Also

mixDesign.c, mixDesign, wirePlot3.

Examples

mdo = mixDesign(3,2, center = FALSE, axial = FALSE, randomize = FALSE,
                replicates  = c(1,1,2,3))
mdo$names(c("polyethylene", "polystyrene", "polypropylene"))
mdo$units("percent")
elongation = c(11.0, 12.4, 15.0, 14.8, 16.1, 17.7, 16.4, 16.6, 8.8, 10.0, 10.0,
               9.7, 11.8, 16.8, 16.0)
mdo$.response(elongation)
contourPlot3(A, B, C, elongation, data = mdo, form = "linear")
contourPlot3(A, B, C, elongation, data = mdo, form = "quadratic", col = 2)
contourPlot3(A, B, C, elongation, data = mdo,
             form = "elongation ~ I(A^2) - B:A + I(C^2)",
             col = 3, axes = FALSE)
contourPlot3(A, B, C, elongation, data = mdo,
             form = "quadratic",
             col = c("yellow", "white", "red"),
             axes = FALSE)

desOpt-class: Class 'desOpt'

Description

The desOpt class represents an object that stores optimization results for factorial design experiments. It includes coded and real factors, responses, desirabilities, overall desirability, and the design object.

Public fields

Methods

Public methods

• desOpt$as.data.frame()

• desOpt$print()

• desOpt$clone()

Method as.data.frame()

Convert the object to a data frame.

Usage

desOpt$as.data.frame()

Method print()

Print a summary of the object.

Usage

desOpt$print()

Method clone()

The objects of this class are cloneable with this method.

Usage

desOpt$clone(deep = FALSE)

Arguments

See Also

optimum, facDesign, desirability

desirability: Desirability Function.

Description

Creates desirability functions for use in the optimization of multiple responses.

Usage

desirability(
  response,
  low,
  high,
  target = "max",
  scale = c(1, 1),
  importance = 1
)

Arguments

Details

For a product to be developed, different values of responses are desired, leading to multiple response optimization. Minimization, maximization, as well as a specific target value, are defined using desirability functions. A desirability function transforms the values of a response into [0,1], where 0 stands for a non-acceptable value of the response and 1 for values where higher/lower (depending on the direction of the optimization) values of the response have little merit. This function builds upon the desirability functions specified by Harrington (1965) and the modifications by Derringer and Suich (1980) and Derringer (1994). Castillo, Montgomery, and McCarville (1996) further extended these functions, but these extensions are not implemented in this version.

Value

This function returns a desirability.c object.

See Also

overall, optimum

Examples

# Example 1: Maximization of a response
# Define a desirability for response y where higher values of y are better
# as long as the response is smaller than high
d = desirability(y, low = 6, high = 18, target = "max")
# Show and plot the desirability function
d
plot(d)

# Example 2: Minimization of a response including a scaling factor
# Define a desirability for response y where lower values of y are better
# as long as the response is higher than low
d = desirability(y, low = 6, high = 18, scale = c(2), target = "min")
# Show and plot the desirability function
d
plot(d)

# Example 3: Specific target of a response is best including a scaling factor
# Define a desirability for response y where desired value is at 8 and
# values lower than 6 as well as values higher than 18 are not acceptable
d = desirability(y, low = 6, high = 18, scale = c(0.5, 2), target = 12)
# Show and plot the desirability function
d
plot(d)

# Example 4:
y1 <- c(102, 120, 117, 198, 103, 132, 132, 139, 102, 154, 96, 163, 116, 153,
        133, 133, 140, 142, 145, 142)
y2 <- c(470, 410, 570, 240, 640, 270, 410, 380, 590, 260, 520, 380, 520, 290,
        380, 380, 430, 430, 390, 390)
d1 <- desirability(y1, 120, 170, scale = c(1, 1), target = "max")
d3 <- desirability(y2, 400, 600, target = 500)
d1
plot(d1)
d3
plot(d3)

desirability-class: Class 'desirability'

Description

A class representing the desirability metrics for responses in a design.

Public fields

Methods

Public methods

• desirability.c$new()

• desirability.c$print()

• desirability.c$plot()

• desirability.c$clone()

Method new()

Initializes a new desirability.c object with specified parameters.

Usage

desirability.c$new(
  response = NULL,
  low = NULL,
  high = NULL,
  target = NULL,
  scale = NULL,
  importance = NULL
)

Arguments

Method print()

Prints the details of a desirability.c object.

Usage

desirability.c$print()

Method plot()

Plots the desirability functions based on the specified parameters.

Usage

desirability.c$plot(scale, main, xlab, ylab, line.width, col, numPoints = 500)

Arguments

Method clone()

The objects of this class are cloneable with this method.

Usage

desirability.c$clone(deep = FALSE)

Arguments

See Also

desirability, overall, optimum

dgamma3: The gamma Distribution (3 Parameter)

Description

Density function, distribution function, and quantile function for the Gamma distribution.

Usage

dgamma3(x, shape, scale, threshold)

Arguments

Details

The Gamma distribution with scale parameter alpha, shape parameter c, and threshold parameter zeta has a density given by:

f(x) = \frac{c}{\alpha}\left(\frac{x-\zeta}{\alpha}\right)^{c-1}\exp\left(-\left(\frac{x-\zeta}{\alpha}\right)^c\right)

The cumulative distribution function is given by:

F(x) = 1 - \exp\left(-\left(\frac{x-\zeta}{\alpha}\right)^c\right)

Value

dgamma3 gives the density, pgamma3 gives the distribution function, and qgamma3 gives the quantile function.

Examples

dgamma3(x = 1, scale = 1, shape = 5, threshold = 0)
temp <- pgamma3(q = 1, scale = 1, shape = 5, threshold = 0)
temp
qgamma3(p = temp, scale = 1, shape = 5, threshold = 0)

distribution: Distribution

Description

Calculates the most likely parameters for a given distribution.

Usage

distribution(x = NULL, distrib = "weibull", ...)

Arguments

Value

distribution() returns an object of class DistrCollection.

See Also

Distr, DistrCollection

Examples

data1 <- rnorm(100, mean = 5, sd = 2)
distribution(data1, distrib = "normal")

dlnorm3: The Lognormal Distribution (3 Parameter)

Description

Density function, distribution function, and quantile function for the Lognormal distribution.

Usage

dlnorm3(x, meanlog, sdlog, threshold)

Arguments

Details

The Lognormal distribution with meanlog parameter zeta, sdlog parameter sigma, and threshold parameter theta has a density given by:

f(x) = \frac{1}{\sqrt{2\pi}\sigma(x-\theta)}\exp\left(-\frac{(\log(x-\theta)-\zeta)^2}{2\sigma^2}\right)

The cumulative distribution function is given by:

F(x) = \Phi\left(\frac{\log(x-\theta)-\zeta}{\sigma}\right)

where \Phi is the cumulative distribution function of the standard normal distribution.

Value

dlnorm3 gives the density, plnorm3 gives the distribution function, and qlnorm3 gives the quantile function.

Examples

dlnorm3(x = 2, meanlog = 0, sdlog = 1/8, threshold = 1)
temp <- plnorm3(q = 2, meanlog = 0, sdlog = 1/8, threshold = 1)
temp
qlnorm3(p = temp, meanlog = 0, sdlog = 1/8, threshold = 1)

doeFactor-class: Class 'doeFactor'

Description

An R6 class representing a factor in a design of experiments (DOE).

Public fields

Methods

Public methods

• doeFactor$attributes()

• doeFactor$.low()

• doeFactor$.high()

• doeFactor$.type()

• doeFactor$.unit()

• doeFactor$names()

• doeFactor$print()

• doeFactor$clone()

Method attributes()

Get the attributes of the factor.

Usage

doeFactor$attributes()

Method .low()

Get and set the lower bound for the factor.

Usage

doeFactor$.low(value)

Arguments

Method .high()

Get and set the upper bound for the factor.

Usage

doeFactor$.high(value)

Arguments

Method .type()

Get and set the type of the factor.

Usage

doeFactor$.type(value)

Arguments

Method .unit()

Get and set the unit of measurement for the factor.

Usage

doeFactor$.unit(value)

Arguments

Method names()

Get and set the name of the factor.

Usage

doeFactor$names(value)

Arguments

Method print()

Print the characteristics of the factors.

Usage

doeFactor$print()

Method clone()

The objects of this class are cloneable with this method.

Usage

doeFactor$clone(deep = FALSE)

Arguments

See Also

taguchiFactor

dotPlot: Function to create a dot plot

Description

Creates a dot plot. For data in groups, the dot plot can be displayed stacked or in separate regions.

Usage

dotPlot(
  x,
  group,
  xlim,
  ylim,
  col,
  xlab,
  ylab,
  pch,
  cex,
  breaks,
  stacked = TRUE,
  main,
  showPlot = TRUE
)

Arguments

Details

Values in x are assigned to the bins defined by breaks. The binning is performed using hist.

Value

A list cointaining:

• An invisible matrix containing NAs and numeric values representing values in a bin. The number of bins is given by the number of columns of the matrix.

• The graphic.

Examples

# Create some data and grouping
set.seed(1)
x <- rnorm(28)
g <- rep(1:2, 14)

# Dot plot with groups and no stacking
dotPlot(x, group = g, stacked = FALSE, pch = c(19, 20), main = "Non stacked dot plot")

# Dot plot with groups and stacking
dotPlot(x, group = g, stacked = TRUE, pch = c(19, 20), main = "Stacked dot plot")

dweibull3: The Weibull Distribution (3 Parameter)

Description

Density function, distribution function, and quantile function for the Weibull distribution with a threshold parameter.

Usage

dweibull3(x, shape, scale, threshold)

Arguments

Details

The Weibull distribution with the scale parameter alpha, shape parameter c, and threshold parameter zeta has a density function given by:

f(x) = \frac{c}{\alpha} \left(\frac{x - \zeta}{\alpha}\right)^{c-1} \exp\left(-\left(\frac{x - \zeta}{\alpha}\right)^c\right)

The cumulative distribution function is given by:

F(x) = 1 - \exp\left(-\left(\frac{x - \zeta}{\alpha}\right)^c\right)

Value

dweibull3 returns the density, pweibull3 returns the distribution function, and qweibull3 returns the quantile function for the Weibull distribution with a threshold.

Examples

dweibull3(x = 1, scale = 1, shape = 5, threshold = 0)
temp <- pweibull3(q = 1, scale = 1, shape = 5, threshold = 0)
temp
qweibull3(p = temp, scale = 1, shape = 5, threshold = 0)

facDesign

Description

Generates a 2^k full factorial design.

Usage

facDesign(
  k = 3,
  p = 0,
  replicates = 1,
  blocks = 1,
  centerCube = 0,
  random.seed = 1234
)

Arguments

Value

The function facDesign returns an object of class facDesign.c.

See Also

fracDesign, fracChoose, rsmDesign, pbDesign, taguchiDesign

Examples

# Example 1
vp.full <- facDesign(k = 3)
vp.full$.response(rnorm(2^3))
vp.full$summary()

# Example 2
vp.rep <- facDesign(k = 2, replicates = 3, centerCube = 4)
vp.rep$names(c("Name 1", "Name 2"))
vp.rep$unit(c("min", "F"))
vp.rep$lows(c(20, 40, 60))
vp.rep$highs(c(40, 60, 80))
vp.rep$summary()

# Example 3
dfac <- facDesign(k = 3, centerCube = 4)
dfac$names(c('Factor 1', 'Factor 2', 'Factor 3'))
dfac$names()
dfac$lows(c(80, 120, 1))
dfac$lows()
dfac$highs(c(120, 140, 2))
dfac$highs()
dfac$summary()

facDesign-class: Class 'facDesign'

Description

The facDesign.c class is used to represent factorial designs, including their factors, responses, blocks, and design matrices. This class supports various experimental designs and allows for the storage and manipulation of data related to the design and analysis of factorial experiments.

Public fields

Methods

Public methods

• facDesign.c$nrow()

• facDesign.c$ncol()

• facDesign.c$print()

• facDesign.c$.clear()

• facDesign.c$names()

• facDesign.c$as.data.frame()

• facDesign.c$get()

• facDesign.c$lows()

• facDesign.c$highs()

• facDesign.c$.nfp()

• facDesign.c$identity()

• facDesign.c$summary()

• facDesign.c$.response()

• facDesign.c$effectPlot()

• facDesign.c$lm()

• facDesign.c$desires()

• facDesign.c$set.fits()

• facDesign.c$types()

• facDesign.c$unit()

• facDesign.c$.star()

• facDesign.c$.blockGen()

• facDesign.c$.block()

• facDesign.c$.centerCube()

• facDesign.c$.centerStar()

• facDesign.c$.generators()

• facDesign.c$clone()

Method nrow()

Get the number of rows Design.

Usage

facDesign.c$nrow()

Method ncol()

Get the number of columns Design.

Usage

facDesign.c$ncol()

Method print()

Prints a formatted representation of the factorial design object, including design matrices and responses.

Usage

facDesign.c$print()

Method .clear()

Clears the factorial design object.

Usage

facDesign.c$.clear()

Method names()

Get or set the names of the factors in the factorial design.

Usage

facDesign.c$names(value)

Arguments

Method as.data.frame()

Converts the factorial design object to a data frame.

Usage

facDesign.c$as.data.frame()

Method get()

Retrieves elements from the factorial design object.

Usage

facDesign.c$get(i, j)

Arguments

Method lows()

Get or set the lower bounds of the factors in the factorial design.

Usage

facDesign.c$lows(value)

Arguments

Method highs()

Get or set the upper bounds of the factors in the factorial design.

Usage

facDesign.c$highs(value)

Arguments

Method .nfp()

Prints a summary of the factors attributes including their low, high, name, unit, and type.

Usage

facDesign.c$.nfp()

Method identity()

Returns the factorial design object itself, used to verify or return the object.

Usage

facDesign.c$identity()

Method summary()

Summarizes the factorial design object.

Usage

facDesign.c$summary()

Method .response()

Get or set the response data in the factorial design object.

Usage

facDesign.c$.response(value)

Arguments

Method effectPlot()

Plots the effects of factors on the response variables.

Usage

facDesign.c$effectPlot(
  factors,
  fun = mean,
  response = NULL,
  lty,
  xlab,
  ylab,
  main,
  ylim
)

Arguments

Method lm()

Fits a linear model to the response data in the factorial design object.

Usage

facDesign.c$lm(formula)

Arguments

Method desires()

Get or set the desirability values for the response variables.

Usage

facDesign.c$desires(value)

Arguments

Method set.fits()

Set the fits for the response variables in the factorial design object.

Usage

facDesign.c$set.fits(value)

Arguments

Method types()

Get or set the types of designs used in the factorial design object.

Usage

facDesign.c$types(value)

Arguments

Method unit()

Get or set the units for the factors in the factorial design object.

Usage

facDesign.c$unit(value)

Arguments

Method .star()

Get or set the star points in the factorial design object.

Usage

facDesign.c$.star(value)

Arguments

Method .blockGen()

Get or set the block generators in the factorial design object.

Usage

facDesign.c$.blockGen(value)

Arguments

Method .block()

Get or set the blocks in the factorial design object.

Usage

facDesign.c$.block(value)

Arguments

Method .centerCube()

Get or set the center points in the cube portion of the factorial design.

Usage

facDesign.c$.centerCube(value)

Arguments

Method .centerStar()

Get or set the center points in the star portion of the factorial design.

Usage

facDesign.c$.centerStar(value)

Arguments

Method .generators()

Get or set the generators for the factorial design.

Usage

facDesign.c$.generators(value)

Arguments

Method clone()

The objects of this class are cloneable with this method.

Usage

facDesign.c$clone(deep = FALSE)

Arguments

See Also

mixDesign.c, taguchiDesign.c.

fracChoose: Choosing a fractional or full factorial design from a table.

Description

Designs displayed are the classic minimum abberation designs. Choosing a design is done by clicking with the mouse into the appropriate field.

Usage

fracChoose()

Value

fracChoose returns an object of class facDesign.c.

See Also

fracDesign, facDesign, rsmChoose, rsmDesign

Examples

fracChoose()

fracDesign

Description

Generates a 2^k-p fractional factorial design.

Usage

fracDesign(
  k = 3,
  p = 0,
  gen = NULL,
  replicates = 1,
  blocks = 1,
  centerCube = 0,
  random.seed = 1234
)

Arguments

Value

The function fracDesign returns an object of class facDesign.c.

See Also

facDesign, fracChoose, rsmDesign, pbDesign, taguchiDesign

Examples

#Example 1
#Returns a 2^4-1 fractional factorial design. Factor D will be aliased with
vp.frac = fracDesign(k = 4, gen = "D=ABC")
#the three-way-interaction ABC (i.e. I = ABCD)
vp.frac$.response(rnorm(2^(4-1)))
# summary of the fractional factorial design
vp.frac$summary()

#Example 2
#Returns a full factorial design with 3 replications per factor combination and 4 center points
vp.rep = fracDesign(k = 3, replicates = 3, centerCube = 4)
#Summary of the replicated fractional factorial design
vp.rep$summary()

gageLin: Function to visualize and calucalte the linearity of a gage.

Description

Function visualize the linearity of a gage by plotting the single and mean bias in one plot and intercalate them with a straight line. Furthermore the function deliver some characteristic values of linearity studies according to MSA (Measurement System Analysis).

Usage

gageLin(
  object,
  conf.level = 0.95,
  ylim,
  col,
  pch,
  lty = c(1, 2),
  stats = TRUE,
  plot = TRUE
)

Arguments

Value

The function returns an object of class MSALinearity which can be used with e.g. plot or summary.

See Also

cg, gageRR, gageLinDesign, MSALinearity.

Examples

# Results of single runs
A=c(2.7,2.5,2.4,2.5,2.7,2.3,2.5,2.5,2.4,2.4,2.6,2.4)
B=c(5.1,3.9,4.2,5,3.8,3.9,3.9,3.9,3.9,4,4.1,3.8)
C=c(5.8,5.7,5.9,5.9,6,6.1,6,6.1,6.4,6.3,6,6.1)
D=c(7.6,7.7,7.8,7.7,7.8,7.8,7.8,7.7,7.8,7.5,7.6,7.7)
E=c(9.1,9.3,9.5,9.3,9.4,9.5,9.5,9.5,9.6,9.2,9.3,9.4)

# create Design
test=gageLinDesign(ref=c(2,4,6,8,10),n=12)
# create data.frame for results
results=data.frame(rbind(A,B,C,D,E))
# enter results in Design
test$response(results)
test$summary()

# no plot and no return
MSALin=gageLin(test,stats=FALSE,plot=FALSE)

# plot only
plot(MSALin)
MSALin$plot()

# summary
MSALin$summary()

gageLinDesign: Function to create a object of class MSALinearity.

Description

Function generates an object that can be used with the function gageLin.

Usage

gageLinDesign(ref, n = 5)

Arguments

Value

The function returns an object of class MSALinearity.

See Also

MSALinearity, gageLin.

Examples

# results of run A-E
A=c(2.7,2.5,2.4,2.5,2.7,2.3,2.5,2.5,2.4,2.4,2.6,2.4)
B=c(5.1,3.9,4.2,5,3.8,3.9,3.9,3.9,3.9,4,4.1,3.8)
C=c(5.8,5.7,5.9,5.9,6,6.1,6,6.1,6.4,6.3,6,6.1)
D=c(7.6,7.7,7.8,7.7,7.8,7.8,7.8,7.7,7.8,7.5,7.6,7.7)
E=c(9.1,9.3,9.5,9.3,9.4,9.5,9.5,9.5,9.6,9.2,9.3,9.4)

# create Design
test=gageLinDesign(ref=c(2,4,6,8,10),n=12)
# create data.frame for results
results=data.frame(rbind(A,B,C,D,E))
# enter results in Design
test$response(results)

gageRR: Gage R&R - Gage Repeatability and Reproducibility

Description

Performs a Gage R&R analysis for an object of class gageRR.c.

Usage

gageRR(
  gdo,
  method = "crossed",
  sigma = 6,
  alpha = 0.25,
  tolerance = NULL,
  dig = 3,
  print = TRUE
)

Arguments

Value

The function gageRR returns an object of class gageRR.c and shows typical Gage Repeatability and Reproducibility Output including Process to Tolerance Ratios and the number of distinctive categories (i.e. ndc) the measurement system is able to discriminate with the tested setting.

See Also

gageRR.c, gageRRDesign, gageLin, cg.

Examples

# Create de gageRR Design
design <- gageRRDesign(Operators = 3, Parts = 10, Measurements = 3,
                       method = "crossed", sigma = 6, randomize = TRUE)
design$response(rnorm(nrow(design$X), mean = 10, sd = 2))

# Results of de Design
result <- gageRR(gdo = design, method = "crossed", sigma = 6, alpha = 0.25)
class(result)
result$plot()

gageRR-class: Class 'gageRR'

Description

R6 Class for Gage R&R (Repeatability and Reproducibility) Analysis

Public fields

Methods

Public methods

• gageRR.c$new()

• gageRR.c$print()

• gageRR.c$subset()

• gageRR.c$summary()

• gageRR.c$get.response()

• gageRR.c$response()

• gageRR.c$names()

• gageRR.c$as.data.frame()

• gageRR.c$get.tolerance()

• gageRR.c$set.tolerance()

• gageRR.c$get.sigma()

• gageRR.c$set.sigma()

• gageRR.c$plot()

• gageRR.c$errorPlot()

• gageRR.c$whiskersPlot()

• gageRR.c$averagePlot()

• gageRR.c$compPlot()

• gageRR.c$clone()

Method new()

Initialize the fiels of the gageRR object

Usage

gageRR.c$new(
  X,
  ANOVA = NULL,
  RedANOVA = NULL,
  method = NULL,
  Estimates = NULL,
  Varcomp = NULL,
  Sigma = NULL,
  GageName = NULL,
  GageTolerance = NULL,
  DateOfStudy = NULL,
  PersonResponsible = NULL,
  Comments = NULL,
  b = NULL,
  a = NULL,
  y = NULL,
  facNames = NULL,
  numO = NULL,
  numP = NULL,
  numM = NULL
)

Arguments

Method print()

Return the data frame containing the measurement data (X)

Usage

gageRR.c$print()

Method subset()

Return a subset of the data frame that containing the measurement data (X)

Usage

gageRR.c$subset(i, j)

Arguments

Method summary()

Summarize the information of the fields of the gageRR object.

Usage

gageRR.c$summary()

Method get.response()

Get or get the response for a gageRRDesign object.

Usage

gageRR.c$get.response()

Method response()

Set the response for a gageRRDesign object.

Usage

gageRR.c$response(value)

Arguments

Method names()

Methods for function names in Package base.

Usage

gageRR.c$names()

Method as.data.frame()

Methods for function as.data.frame in Package base.

Usage

gageRR.c$as.data.frame()

Method get.tolerance()

Get the tolerance for an object of class gageRR.

Usage

gageRR.c$get.tolerance()

Method set.tolerance()

Set the tolerance for an object of class gageRR.

Usage

gageRR.c$set.tolerance(value)

Arguments

Method get.sigma()

Get the sigma for an object of class gageRR.

Usage

gageRR.c$get.sigma()

Method set.sigma()

Set the sigma for an object of class gageRR.

Usage

gageRR.c$set.sigma(value)

Arguments

Method plot()

This function creates a customized plot using the data from the gageRR.c object.

Usage

gageRR.c$plot(main = NULL, xlab = NULL, ylab = NULL, col, lwd, fun = mean)

Arguments

Examples

# Create gageRR-object
gdo = gageRRDesign(Operators = 3, Parts = 10, Measurements = 3, randomize = FALSE)
# Vector of responses
y = c(0.29,0.08, 0.04,-0.56,-0.47,-1.38,1.34,1.19,0.88,0.47,0.01,0.14,-0.80,
      -0.56,-1.46, 0.02,-0.20,-0.29,0.59,0.47,0.02,-0.31,-0.63,-0.46,2.26,
      1.80,1.77,-1.36,-1.68,-1.49,0.41,0.25,-0.11,-0.68,-1.22,-1.13,1.17,0.94,
      1.09,0.50,1.03,0.20,-0.92,-1.20,-1.07,-0.11, 0.22,-0.67,0.75,0.55,0.01,
      -0.20, 0.08,-0.56,1.99,2.12,1.45,-1.25,-1.62,-1.77,0.64,0.07,-0.15,-0.58,
      -0.68,-0.96,1.27,1.34,0.67,0.64,0.20,0.11,-0.84,-1.28,-1.45,-0.21,0.06,
      -0.49,0.66,0.83,0.21,-0.17,-0.34,-0.49,2.01,2.19,1.87,-1.31,-1.50,-2.16)

# Appropriate responses
gdo$response(y)
# Perform and gageRR
gdo <- gageRR(gdo)

gdo$plot()

Method errorPlot()

The data from an object of class gageRR can be analyzed by running 'Error Charts' of the individual deviations from the accepted rference values. These 'Error Charts' are provided by the function errorPlot.

Usage

gageRR.c$errorPlot(main, xlab, ylab, col, pch, ylim, legend = TRUE)

Arguments

Examples

# Create gageRR-object
gdo = gageRRDesign(Operators = 3, Parts = 10, Measurements = 3, randomize = FALSE)
# Vector of responses
y = c(0.29,0.08, 0.04,-0.56,-0.47,-1.38,1.34,1.19,0.88,0.47,0.01,0.14,-0.80,
      -0.56,-1.46, 0.02,-0.20,-0.29,0.59,0.47,0.02,-0.31,-0.63,-0.46,2.26,
      1.80,1.77,-1.36,-1.68,-1.49,0.41,0.25,-0.11,-0.68,-1.22,-1.13,1.17,0.94,
      1.09,0.50,1.03,0.20,-0.92,-1.20,-1.07,-0.11, 0.22,-0.67,0.75,0.55,0.01,
      -0.20, 0.08,-0.56,1.99,2.12,1.45,-1.25,-1.62,-1.77,0.64,0.07,-0.15,-0.58,
      -0.68,-0.96,1.27,1.34,0.67,0.64,0.20,0.11,-0.84,-1.28,-1.45,-0.21,0.06,
      -0.49,0.66,0.83,0.21,-0.17,-0.34,-0.49,2.01,2.19,1.87,-1.31,-1.50,-2.16)

# Appropriate responses
gdo$response(y)
# Perform and gageRR
gdo <- gageRR(gdo)

gdo$errorPlot()

Method whiskersPlot()

In a Whiskers Chart, the high and low data values and the average (median) by part-by-operator are plotted to provide insight into the consistency between operators, to indicate outliers and to discover part-operator interactions. The Whiskers Chart reminds of boxplots for every part and every operator.

Usage

gageRR.c$whiskersPlot(main, xlab, ylab, col, ylim, legend = TRUE)

Arguments

Examples

# Create gageRR-object
gdo = gageRRDesign(Operators = 3, Parts = 10, Measurements = 3, randomize = FALSE)
# Vector of responses
y = c(0.29,0.08, 0.04,-0.56,-0.47,-1.38,1.34,1.19,0.88,0.47,0.01,0.14,-0.80,
      -0.56,-1.46, 0.02,-0.20,-0.29,0.59,0.47,0.02,-0.31,-0.63,-0.46,2.26,
      1.80,1.77,-1.36,-1.68,-1.49,0.41,0.25,-0.11,-0.68,-1.22,-1.13,1.17,0.94,
      1.09,0.50,1.03,0.20,-0.92,-1.20,-1.07,-0.11, 0.22,-0.67,0.75,0.55,0.01,
      -0.20, 0.08,-0.56,1.99,2.12,1.45,-1.25,-1.62,-1.77,0.64,0.07,-0.15,-0.58,
      -0.68,-0.96,1.27,1.34,0.67,0.64,0.20,0.11,-0.84,-1.28,-1.45,-0.21,0.06,
      -0.49,0.66,0.83,0.21,-0.17,-0.34,-0.49,2.01,2.19,1.87,-1.31,-1.50,-2.16)

# Appropriate responses
gdo$response(y)
# Perform and gageRR
gdo <- gageRR(gdo)

gdo$whiskersPlot()

Method averagePlot()

averagePlot creates all x-y plots of averages by size out of an object of class gageRR. Therfore the averages of the multiple readings by each operator on each part are plotted with the reference value or overall part averages as the index.

Usage

gageRR.c$averagePlot(main, xlab, ylab, col, single = FALSE)

Arguments

Examples

# Create gageRR-object
gdo = gageRRDesign(Operators = 3, Parts = 10, Measurements = 3, randomize = FALSE)
# Vector of responses
y = c(0.29,0.08, 0.04,-0.56,-0.47,-1.38,1.34,1.19,0.88,0.47,0.01,0.14,-0.80,
      -0.56,-1.46, 0.02,-0.20,-0.29,0.59,0.47,0.02,-0.31,-0.63,-0.46,2.26,
      1.80,1.77,-1.36,-1.68,-1.49,0.41,0.25,-0.11,-0.68,-1.22,-1.13,1.17,0.94,
      1.09,0.50,1.03,0.20,-0.92,-1.20,-1.07,-0.11, 0.22,-0.67,0.75,0.55,0.01,
      -0.20, 0.08,-0.56,1.99,2.12,1.45,-1.25,-1.62,-1.77,0.64,0.07,-0.15,-0.58,
      -0.68,-0.96,1.27,1.34,0.67,0.64,0.20,0.11,-0.84,-1.28,-1.45,-0.21,0.06,
      -0.49,0.66,0.83,0.21,-0.17,-0.34,-0.49,2.01,2.19,1.87,-1.31,-1.50,-2.16)

# Appropriate responses
gdo$response(y)
# Perform and gageRR
gdo <- gageRR(gdo)

gdo$averagePlot()

Method compPlot()

compPlot creates comparison x-y plots of an object of class gageRR. The averages of the multiple readings by each operator on each part are plotted against each other with the operators as indices. This plot compares the values obtained by one operator to those of another.

Usage

gageRR.c$compPlot(main, xlab, ylab, col, cex.lab, fun = NULL)

Arguments

Examples

# Create gageRR-object
gdo = gageRRDesign(Operators = 3, Parts = 10, Measurements = 3, randomize = FALSE)
# Vector of responses
y = c(0.29,0.08, 0.04,-0.56,-0.47,-1.38,1.34,1.19,0.88,0.47,0.01,0.14,-0.80,
      -0.56,-1.46, 0.02,-0.20,-0.29,0.59,0.47,0.02,-0.31,-0.63,-0.46,2.26,
      1.80,1.77,-1.36,-1.68,-1.49,0.41,0.25,-0.11,-0.68,-1.22,-1.13,1.17,0.94,
      1.09,0.50,1.03,0.20,-0.92,-1.20,-1.07,-0.11, 0.22,-0.67,0.75,0.55,0.01,
      -0.20, 0.08,-0.56,1.99,2.12,1.45,-1.25,-1.62,-1.77,0.64,0.07,-0.15,-0.58,
      -0.68,-0.96,1.27,1.34,0.67,0.64,0.20,0.11,-0.84,-1.28,-1.45,-0.21,0.06,
      -0.49,0.66,0.83,0.21,-0.17,-0.34,-0.49,2.01,2.19,1.87,-1.31,-1.50,-2.16)

# Appropriate responses
gdo$response(y)
# Perform and gageRR
gdo <- gageRR(gdo)

gdo$compPlot()

Method clone()

The objects of this class are cloneable with this method.

Usage

gageRR.c$clone(deep = FALSE)

Arguments

Examples

#create gageRR-object
gdo <- gageRRDesign(Operators = 3, Parts = 10, Measurements = 3, randomize = FALSE)
#vector of responses
y <- c(0.29,0.08, 0.04,-0.56,-0.47,-1.38,1.34,1.19,0.88,0.47,0.01,0.14,-0.80,
      -0.56,-1.46, 0.02,-0.20,-0.29,0.59,0.47,0.02,-0.31,-0.63,-0.46,2.26,
      1.80,1.77,-1.36,-1.68,-1.49,0.41,0.25,-0.11,-0.68,-1.22,-1.13,1.17,0.94,
      1.09,0.50,1.03,0.20,-0.92,-1.20,-1.07,-0.11, 0.22,-0.67,0.75,0.55,0.01,
      -0.20, 0.08,-0.56,1.99,2.12,1.45,-1.25,-1.62,-1.77,0.64,0.07,-0.15,-0.58,
      -0.68,-0.96,1.27,1.34,0.67,0.64,0.20,0.11,-0.84,-1.28,-1.45,-0.21,0.06,
      -0.49,0.66,0.83,0.21,-0.17,-0.34,-0.49,2.01,2.19,1.87,-1.31,-1.50,-2.16)

#appropriate responses
gdo$response(y)
# perform and gageRR
gdo <- gageRR(gdo)

# Using the plots
gdo$plot()

## ------------------------------------------------
## Method `gageRR.c$plot`
## ------------------------------------------------

# Create gageRR-object
gdo = gageRRDesign(Operators = 3, Parts = 10, Measurements = 3, randomize = FALSE)
# Vector of responses
y = c(0.29,0.08, 0.04,-0.56,-0.47,-1.38,1.34,1.19,0.88,0.47,0.01,0.14,-0.80,
      -0.56,-1.46, 0.02,-0.20,-0.29,0.59,0.47,0.02,-0.31,-0.63,-0.46,2.26,
      1.80,1.77,-1.36,-1.68,-1.49,0.41,0.25,-0.11,-0.68,-1.22,-1.13,1.17,0.94,
      1.09,0.50,1.03,0.20,-0.92,-1.20,-1.07,-0.11, 0.22,-0.67,0.75,0.55,0.01,
      -0.20, 0.08,-0.56,1.99,2.12,1.45,-1.25,-1.62,-1.77,0.64,0.07,-0.15,-0.58,
      -0.68,-0.96,1.27,1.34,0.67,0.64,0.20,0.11,-0.84,-1.28,-1.45,-0.21,0.06,
      -0.49,0.66,0.83,0.21,-0.17,-0.34,-0.49,2.01,2.19,1.87,-1.31,-1.50,-2.16)

# Appropriate responses
gdo$response(y)
# Perform and gageRR
gdo <- gageRR(gdo)

gdo$plot()

## ------------------------------------------------
## Method `gageRR.c$errorPlot`
## ------------------------------------------------

# Create gageRR-object
gdo = gageRRDesign(Operators = 3, Parts = 10, Measurements = 3, randomize = FALSE)
# Vector of responses
y = c(0.29,0.08, 0.04,-0.56,-0.47,-1.38,1.34,1.19,0.88,0.47,0.01,0.14,-0.80,
      -0.56,-1.46, 0.02,-0.20,-0.29,0.59,0.47,0.02,-0.31,-0.63,-0.46,2.26,
      1.80,1.77,-1.36,-1.68,-1.49,0.41,0.25,-0.11,-0.68,-1.22,-1.13,1.17,0.94,
      1.09,0.50,1.03,0.20,-0.92,-1.20,-1.07,-0.11, 0.22,-0.67,0.75,0.55,0.01,
      -0.20, 0.08,-0.56,1.99,2.12,1.45,-1.25,-1.62,-1.77,0.64,0.07,-0.15,-0.58,
      -0.68,-0.96,1.27,1.34,0.67,0.64,0.20,0.11,-0.84,-1.28,-1.45,-0.21,0.06,
      -0.49,0.66,0.83,0.21,-0.17,-0.34,-0.49,2.01,2.19,1.87,-1.31,-1.50,-2.16)

# Appropriate responses
gdo$response(y)
# Perform and gageRR
gdo <- gageRR(gdo)

gdo$errorPlot()

## ------------------------------------------------
## Method `gageRR.c$whiskersPlot`
## ------------------------------------------------

# Create gageRR-object
gdo = gageRRDesign(Operators = 3, Parts = 10, Measurements = 3, randomize = FALSE)
# Vector of responses
y = c(0.29,0.08, 0.04,-0.56,-0.47,-1.38,1.34,1.19,0.88,0.47,0.01,0.14,-0.80,
      -0.56,-1.46, 0.02,-0.20,-0.29,0.59,0.47,0.02,-0.31,-0.63,-0.46,2.26,
      1.80,1.77,-1.36,-1.68,-1.49,0.41,0.25,-0.11,-0.68,-1.22,-1.13,1.17,0.94,
      1.09,0.50,1.03,0.20,-0.92,-1.20,-1.07,-0.11, 0.22,-0.67,0.75,0.55,0.01,
      -0.20, 0.08,-0.56,1.99,2.12,1.45,-1.25,-1.62,-1.77,0.64,0.07,-0.15,-0.58,
      -0.68,-0.96,1.27,1.34,0.67,0.64,0.20,0.11,-0.84,-1.28,-1.45,-0.21,0.06,
      -0.49,0.66,0.83,0.21,-0.17,-0.34,-0.49,2.01,2.19,1.87,-1.31,-1.50,-2.16)

# Appropriate responses
gdo$response(y)
# Perform and gageRR
gdo <- gageRR(gdo)

gdo$whiskersPlot()

## ------------------------------------------------
## Method `gageRR.c$averagePlot`
## ------------------------------------------------

# Create gageRR-object
gdo = gageRRDesign(Operators = 3, Parts = 10, Measurements = 3, randomize = FALSE)
# Vector of responses
y = c(0.29,0.08, 0.04,-0.56,-0.47,-1.38,1.34,1.19,0.88,0.47,0.01,0.14,-0.80,
      -0.56,-1.46, 0.02,-0.20,-0.29,0.59,0.47,0.02,-0.31,-0.63,-0.46,2.26,
      1.80,1.77,-1.36,-1.68,-1.49,0.41,0.25,-0.11,-0.68,-1.22,-1.13,1.17,0.94,
      1.09,0.50,1.03,0.20,-0.92,-1.20,-1.07,-0.11, 0.22,-0.67,0.75,0.55,0.01,
      -0.20, 0.08,-0.56,1.99,2.12,1.45,-1.25,-1.62,-1.77,0.64,0.07,-0.15,-0.58,
      -0.68,-0.96,1.27,1.34,0.67,0.64,0.20,0.11,-0.84,-1.28,-1.45,-0.21,0.06,
      -0.49,0.66,0.83,0.21,-0.17,-0.34,-0.49,2.01,2.19,1.87,-1.31,-1.50,-2.16)

# Appropriate responses
gdo$response(y)
# Perform and gageRR
gdo <- gageRR(gdo)

gdo$averagePlot()

## ------------------------------------------------
## Method `gageRR.c$compPlot`
## ------------------------------------------------

# Create gageRR-object
gdo = gageRRDesign(Operators = 3, Parts = 10, Measurements = 3, randomize = FALSE)
# Vector of responses
y = c(0.29,0.08, 0.04,-0.56,-0.47,-1.38,1.34,1.19,0.88,0.47,0.01,0.14,-0.80,
      -0.56,-1.46, 0.02,-0.20,-0.29,0.59,0.47,0.02,-0.31,-0.63,-0.46,2.26,
      1.80,1.77,-1.36,-1.68,-1.49,0.41,0.25,-0.11,-0.68,-1.22,-1.13,1.17,0.94,
      1.09,0.50,1.03,0.20,-0.92,-1.20,-1.07,-0.11, 0.22,-0.67,0.75,0.55,0.01,
      -0.20, 0.08,-0.56,1.99,2.12,1.45,-1.25,-1.62,-1.77,0.64,0.07,-0.15,-0.58,
      -0.68,-0.96,1.27,1.34,0.67,0.64,0.20,0.11,-0.84,-1.28,-1.45,-0.21,0.06,
      -0.49,0.66,0.83,0.21,-0.17,-0.34,-0.49,2.01,2.19,1.87,-1.31,-1.50,-2.16)

# Appropriate responses
gdo$response(y)
# Perform and gageRR
gdo <- gageRR(gdo)

gdo$compPlot()

gageRRDesign: Gage R&R - Gage Repeatability and Reproducibility

Description

Function to Creates a Gage R&R design.

Usage

gageRRDesign(
  Operators = 3,
  Parts = 10,
  Measurements = 3,
  method = "crossed",
  sigma = 6,
  randomize = TRUE
)

Arguments

Value

The function gageRRDesign returns an object of class gageRR.

See Also

gageRR.c, gageRR.

Examples

design <- gageRRDesign(Operators = 3, Parts = 10, Measurements = 3,
                       method = "crossed", sigma = 6, randomize = TRUE)

interactionPlot

Description

Creates an interaction plot for the factors in a factorial design to visualize the interaction effects between them.

Usage

interactionPlot(dfac, response = NULL, fun = mean, main, col = 1:2)

Arguments

Details

interactionPlot() displays interactions for an object of class facDesign (i.e. 2^k full or 2^k-p fractional factorial design). Parts of the original interactionPlot were integrated.

Value

Return an interaction plot for the factors in a factorial design.

See Also

fracDesign, facDesign

Examples

# Example 1
# Create the facDesign object
dfac <- facDesign(k = 3, centerCube = 4)
dfac$names(c('Factor 1', 'Factor 2', 'Factor 3'))

# Assign performance to the factorial design
rend <- c(simProc(120,140,1), simProc(80,140,1), simProc(120,140,2),
          simProc(120,120,1), simProc(90,130,1.5), simProc(90,130,1.5),
          simProc(80,120,2), simProc(90,130,1.5), simProc(90,130,1.5),
          simProc(120,120,2), simProc(80,140,2), simProc(80,120,1))
dfac$.response(rend)

# Create an interaction plot
interactionPlot(dfac, fun = mean, col = c("purple", "red"))

# Example 2
vp <- fracDesign(k=3, replicates = 2)
y <- 4*vp$get(j=1) -7*vp$get(j=2) + 2*vp$get(j=2)*vp$get(j=1) +
     0.2*vp$get(j=3) + rnorm(16)
vp$.response(y)

interactionPlot(vp)

mixDesign: Mixture Designs

Description

Function to generate simplex lattice and simplex centroid mixture designs with optional center points and axial points.

Usage

mixDesign(
  p,
  n = 3,
  type = "lattice",
  center = TRUE,
  axial = FALSE,
  delta,
  replicates = 1,
  lower,
  total = 1,
  randomize,
  seed = 1234
)

Arguments

Value

The function mixDesig() returns an object of class mixDesig().

Note

In this version the creation of (augmented) lattice, centroid mixture designs is fully supported. Getters and Setter methods for the mixDesign object exist just as for objects of class facDesign (i.e. factorial designs).

The creation of constrained component proportions is partially supported but don't rely on it. Visualization (i.e. ternary plots) for some of these designs can be done with the help of the wirePlot3 and contourPlot3 function.

See Also

mixDesign.c, facDesign.c, facDesign, fracDesign, rsmDesign, wirePlot3, contourPlot3.

Examples

# Example usage of mixDesign
mdo <- mixDesign(3, 2, center = FALSE, axial = FALSE, randomize = FALSE, replicates = c(1, 1, 2, 3))

mdo$names(c("polyethylene", "polystyrene", "polypropylene"))
elongation <- c(11.0, 12.4, 15.0, 14.8, 16.1, 17.7,
                16.4, 16.6, 8.8, 10.0, 10.0, 9.7,
                11.8, 16.8, 16.0)
mdo$.response(elongation)

mdo$units()
mdo$summary()

mixDesign-class: Class 'mixDesign'

Description

mixDesign class for simplex lattice and simplex centroid mixture designs with optional center points and augmented points.

Public fields

Methods

Public methods

• mixDesign.c$.factors()

• mixDesign.c$names()

• mixDesign.c$as.data.frame()

• mixDesign.c$print()

• mixDesign.c$.response()

• mixDesign.c$.nfp()

• mixDesign.c$summary()

• mixDesign.c$units()

• mixDesign.c$lows()

• mixDesign.c$highs()

• mixDesign.c$clone()

Method .factors()

Get and set the factors in an object of class mixDesign

Usage

mixDesign.c$.factors(value)

Arguments

Method names()

Get and set the names in an object of class mixDesign.

Usage

mixDesign.c$names(value)

Arguments

Method as.data.frame()

Methods for function as.data.frame in Package base.

Usage

mixDesign.c$as.data.frame()

Method print()

Methods for function print in Package base.

Usage

mixDesign.c$print()

Method .response()

Get and set the the response in an object of class mixDesign.

Usage

mixDesign.c$.response(value)

Arguments

Method .nfp()

Prints a summary of the factors attributes including their low, high, name, unit, and type.

Usage

mixDesign.c$.nfp()

Method summary()

Methods for function summary in Package base.

Usage

mixDesign.c$summary()

Method units()

Get and set the units for the factors in an object of class mixDesign.

Usage

mixDesign.c$units(value)

Arguments

Method lows()

Get and set the lows for the factors in an object of class mixDesign.

Usage

mixDesign.c$lows(value)

Arguments

Method highs()

Get and set the highs for the factors in an object of class mixDesign.

Usage

mixDesign.c$highs(value)

Arguments

Method clone()

The objects of this class are cloneable with this method.

Usage

mixDesign.c$clone(deep = FALSE)

Arguments

See Also

mixDesign, contourPlot3, wirePlot3

mvPlot: Function to create a multi-variable plot

Description

Creates a plot for visualizing the relationships between a response variable and multiple factors.

Usage

mvPlot(
  response,
  fac1,
  fac2,
  fac3,
  fac4,
  sort = TRUE,
  col,
  pch,
  labels = FALSE,
  quantile = TRUE,
  FUN = NA
)

Arguments

Value

mvPlot returns an invisible list cointaining: a data.frame in which all plotted points are listed and the final plot. The option labels can be used to plot the row-numbers at the single points and to ease the identification.

Examples

#Example I
examp1 = expand.grid(c("Engine1","Engine2","Engine3"),c(10,20,30,40))
examp1 = as.data.frame(rbind(examp1, examp1, examp1))
examp1 = cbind(examp1, rnorm(36, 1, 0.02))
names(examp1) = c("factor1", "factor2", "response")
mvPlot(response = examp1[,3], fac1 = examp1[,2],fac2 = examp1[,1],sort=FALSE,FUN=mean)

normalPlot: Normal plot

Description

Creates a normal probability plot for the effects in a facDesign.c object.

Usage

normalPlot(
  dfac,
  response = NULL,
  main,
  ylim,
  xlim,
  xlab,
  ylab,
  pch,
  col,
  border = "red"
)

Arguments

Details

If the given facDesign.c object fdo contains replicates this function will deliver a normal plot i.e.: effects divided by the standard deviation (t-value) will be plotted against an appropriate probability scaling (see: 'ppoints'). If the given facDesign.c object fdo contains no replications the standard error can not be calculated. In that case the function will deliver an effect plot. i.e.: the effects will be plotted against an appropriate probability scaling. (see: 'ppoints').

Value

The function normalPlot returns an invisible list containing:

See Also

facDesign, paretoPlot, interactionPlot

Examples

# Example 1: Create a normal probability plot for a full factorial design
dfac <- facDesign(k = 3, centerCube = 4)
dfac$names(c('Factor 1', 'Factor 2', 'Factor 3'))

# Assign performance to the factorial design
rend <- c(simProc(120,140,1), simProc(80,140,1), simProc(120,140,2),
          simProc(120,120,1), simProc(90,130,1.5), simProc(90,130,1.5),
          simProc(80,120,2), simProc(90,130,1.5), simProc(90,130,1.5),
          simProc(120,120,2), simProc(80,140,2), simProc(80,120,1))
dfac$.response(rend)

normalPlot(dfac)

# Example 2: Create a normal probability plot with custom colors and symbols
normalPlot(dfac, col = "blue", pch = 4)

oaChoose: Taguchi Designs

Description

Shows a matrix of possible taguchi designs.

Usage

oaChoose(factors1, factors2, level1, level2, ia)

Arguments

Details

oaChoose returns possible taguchi designs. Specifying the number of factor1 factors with level1 levels (factors1 = 2, level1 = 3 means 2 factors with 3 factor levels) and factor2 factors with level2 levels and desired interactions one or more taguchi designs are suggested. If all parameters are set to '0', a matrix of possible taguchi designs is shown.

Value

oaChoose returns an object of class taguchiDesign.

See Also

• facDesign: for 2^k factorial designs.

• rsmDesign: for response surface designs.

• fracDesign: for fractional factorial design.

• gageRRDesign: for gage designs.

Examples

oaChoose()

optimum: Optimal factor settings

Description

This function calculates the optimal factor settings based on defined desirabilities and constraints. It supports two approaches: (I) evaluating all possible factor settings via a grid search and (II) using optimization methods such as `optim` or `gosolnp` from the Rsolnp package. Using `optim` initial values for the factors to be optimized over can be set via start. The optimality of the solution depends critically on the starting parameters which is why it is recommended to use type=`gosolnp` although calculation takes a while.

Usage

optimum(fdo, constraints, steps = 25, type = "grid", start)

Arguments

Details

The function allows you to optimize the factor settings either by evaluating a grid of possible settings (type = `grid`) or by using optimization algorithms (type = `optim` or `gosolnp`). The choice of optimization method may significantly affect the result, especially for desirability functions that lack continuous first derivatives. When using type = `optim`, it is advisable to provide start values to avoid local optima. The `gosolnp` method is recommended for its robustness, although it may be computationally intensive.

Value

Return an object of class desOpt.

See Also

overall, desirability,

Examples

#Example 1: Simultaneous Optimization of Several Response Variables
#Define the response surface design as given in the paper and sort via Standard Order
fdo = rsmDesign(k = 3, alpha = 1.633, cc = 0, cs = 6)
fdo = randomize(fdo, so = TRUE)
#Attaching the 4 responses
y1 = c(102, 120, 117, 198, 103, 132,
        132, 139, 102, 154, 96, 163,
        116, 153, 133, 133, 140, 142,
        145, 142)

y2 = c(900, 860, 800, 2294, 490, 1289,
        1270, 1090, 770, 1690, 700, 1540,
        2184, 1784, 1300, 1300, 1145, 1090,
        1260, 1344)

y3 = c(470, 410, 570, 240, 640, 270,
        410, 380, 590, 260, 520, 380,
        520, 290, 380, 380, 430, 430,
        390, 390)

y4 = c(67.5, 65, 77.5, 74.5, 62.5, 67,
        78, 70, 76, 70, 63, 75,
        65, 71, 70, 68.5, 68, 68,
        69, 70)
fdo$.response(data.frame(y1, y2, y3, y4)[c(5,2,3,8,1,6,7,4,9:20),])
#Setting names and real values of the factors
fdo$names(c("silica", "silan", "sulfur"))
fdo$highs(c(1.7, 60, 2.8))
fdo$lows(c(0.7, 40, 1.8))
#Setting the desires
fdo$desires(desirability(y1, 120, 170, scale = c(1,1), target = "max"))
fdo$desires(desirability(y2, 1000, 1300, target = "max"))
fdo$desires(desirability(y3, 400, 600, target = 500))
fdo$desires(desirability(y4, 60, 75, target = 67.5))
#Setting the fits
fdo$set.fits(fdo$lm(y1 ~ A + B + C + A:B + A:C + B:C + I(A^2) + I(B^2) + I(C^2)))
fdo$set.fits(fdo$lm(y2 ~ A + B + C + A:B + A:C + B:C + I(A^2) + I(B^2) + I(C^2)))
fdo$set.fits(fdo$lm(y3 ~ A + B + C + A:B + A:C + B:C + I(A^2) + I(B^2) + I(C^2)))
fdo$set.fits(fdo$lm(y4 ~ A + B + C + A:B + A:C + B:C + I(A^2) + I(B^2) + I(C^2)))
#Calculate the best factor settings using type = "optim"
optimum(fdo, type = "optim")
#Calculate the best factor settings using type = "grid"
optimum(fdo, type = "grid")

overall: Overall Desirability.

Description

This function calculates the desirability for each response as well as the overall desirability. The resulting data.frame can be used to plot the overall desirability as well as the desirabilities for each response. This function is designed to visualize the desirability approach for multiple response optimization.

Usage

overall(fdo, steps = 20, constraints, ...)

Arguments

Value

A data.frame with a column for each factor, the desirability for each response, and a column for the overall desirability.

See Also

facDesign, rsmDesign, desirability.

Examples

#Example 1: Arbitrary example with random data
rsdo = rsmDesign(k = 2, blocks = 2, alpha = "both")
rsdo$.response(data.frame(y = rnorm(rsdo$nrow()), y2 = rnorm(rsdo$nrow())))
rsdo$set.fits(rsdo$lm(y ~ A*B + I(A^2) + I(B^2)))
rsdo$set.fits(rsdo$lm(y2 ~ A*B + I(A^2) + I(B^2)))
rsdo$desires(desirability(y, -1, 2, scale = c(1, 1), target = "max"))
rsdo$desires(desirability(y2, -1, 0, scale = c(1, 1), target = "min"))
dVals = overall(rsdo, steps = 10, constraints = list(A = c(-0.5,1), B = c(0, 1)))

paretoChart: Pareto Chart

Description

Function to create a Pareto chart, displaying the relative frequency of categories.

Usage

paretoChart(
  x,
  weight,
  main,
  col,
  border,
  xlab,
  ylab = "Frequency",
  percentVec,
  showTable = TRUE,
  showPlot = TRUE
)

Arguments

Value

paretoChart returns a Pareto chart along with a frequency table if showTable is TRUE. Additionally, the function returns an invisible list containing:

Examples

# Example 1: Creating a Pareto chart for defect types
defects1 <- c(rep("E", 62), rep("B", 15), rep("F", 3), rep("A", 10),
              rep("C", 20), rep("D", 10))
paretoChart(defects1)

# Example 2: Creating a Pareto chart with weighted frequencies
defects2 <- c("E", "B", "F", "A", "C", "D")
frequencies <- c(62, 15, 3, 10, 20, 10)
weights <- c(1.5, 2, 0.5, 1, 1.2, 1.8)
names(weights) <- defects2  # Assign names to the weights vector

paretoChart(defects2, weight = frequencies * weights)

paretoPlot

Description

Display standardized effects and interactions of a facDesign.c object in a pareto plot.

Usage

paretoPlot(
  dfac,
  abs = TRUE,
  decreasing = TRUE,
  alpha = 0.05,
  response = NULL,
  ylim,
  xlab,
  ylab,
  main,
  p.col,
  legend_left = TRUE
)

Arguments

Details

paretoPlot displays a pareto plot of effects and interactions for an object of class facDesign (i.e. 2^k full or 2^k-p fractional factorial design). For a given significance level alpha, a critical value is calculated and added to the plot. Standardization is achieved by dividing estimates with their standard error. For unreplicated fractional factorial designs a Lenth Plot is generated.

Value

The function paretoPlot returns an invisible list containing:

See Also

fracDesign, facDesign

Examples

# Create the facDesign object
dfac <- facDesign(k = 3, centerCube = 4)
dfac$names(c('Factor 1', 'Factor 2', 'Factor 3'))

# Assign performance to the factorial design
rend <- c(simProc(120,140,1), simProc(80,140,1), simProc(120,140,2),
          simProc(120,120,1), simProc(90,130,1.5), simProc(90,130,1.5),
          simProc(80,120,2), simProc(90,130,1.5), simProc(90,130,1.5),
          simProc(120,120,2), simProc(80,140,2), simProc(80,120,1))
dfac$.response(rend)

paretoPlot(dfac)
paretoPlot(dfac, decreasing = TRUE, abs = FALSE, p.col = "Pastel1")

pbDesign: Plackett-Burman Designs

Description

Function to create a Plackett-Burman design.

Usage

pbDesign(n, k, randomize = TRUE, replicates = 1)

Arguments

Value

A pbDesign returns an object of class pbDesign.

Note

This function creates Placket-Burman Designs down to n=26. Bigger Designs are not implemented because of lack in practicability. For the creation either the number of factors or the number of trials can be denoted. Wrong combinations will lead to an error message. Originally Placket-Burman-Design are applicable for number of trials divisible by 4. If n is not divisble by 4 this function will take the next larger Placket-Burman Design and truncate the last rows and columns.

See Also

• facDesign: for 2^k factorial designs.

• rsmDesign: for response surface designs.

• fracDesign: for fractional factorial design.

• gageRRDesign: for gage designs.

Examples

pbdo<- pbDesign(n=5)
pbdo$summary()

pbDesign

Description

An R6 class representing a Plackett-Burman design.

Public fields

Methods

Public methods

• pbDesign.c$values()

• pbDesign.c$units()

• pbDesign.c$.factors()

• pbDesign.c$names()

• pbDesign.c$as.data.frame()

• pbDesign.c$print()

• pbDesign.c$.response()

• pbDesign.c$.nfp()

• pbDesign.c$summary()

• pbDesign.c$clone()

Method values()

Get and set the values for an object of class pbDesign.

Usage

pbDesign.c$values(value)

Arguments

Method units()

Get and set the units for an object of class pbDesign.

Usage

pbDesign.c$units(value)

Arguments

Method .factors()

Get and set the factors in an object of class pbDesign.

Usage

pbDesign.c$.factors(value)

Arguments

Method names()

Get and set the names in an object of class pbDesign.

Usage

pbDesign.c$names(value)

Arguments

Method as.data.frame()

Return a data frame with the information of the object pbDesign.

Usage

pbDesign.c$as.data.frame()

Method print()

Methods for function print in Package base.

Usage

pbDesign.c$print()

Method .response()

Get and set the the response in an object of class pbDesign.

Usage

pbDesign.c$.response(value)

Arguments

Method .nfp()

Prints a summary of the factors attributes including their low, high, name, unit, and type.

Usage

pbDesign.c$.nfp()

Method summary()

Methods for function summary in Package base.

Usage

pbDesign.c$summary()

Method clone()

The objects of this class are cloneable with this method.

Usage

pbDesign.c$clone(deep = FALSE)

Arguments

pbFactor

Description

An R6 class representing a factor in a Plackett-Burman design.

Public fields

Methods

Public methods

• pbFactor$attributes()

• pbFactor$.values()

• pbFactor$.unit()

• pbFactor$names()

• pbFactor$clone()

Method attributes()

Get the attributes of the factor.

Usage

pbFactor$attributes()

Method .values()

Get and set the values for the factors in an object of class pbFactor.

Usage

pbFactor$.values(value)

Arguments

Method .unit()

Get and set the units for the factors in an object of class pbFactor.

Usage

pbFactor$.unit(value)

Arguments

Method names()

Get and set the names in an object of class pbFactor.

Usage

pbFactor$names(value)

Arguments

Method clone()

The objects of this class are cloneable with this method.

Usage

pbFactor$clone(deep = FALSE)

Arguments

pcr: Process Capability Indices

Description

Calculates the process capability cp, cpk, cpkL (onesided) and cpkU (onesided) for a given dataset and distribution. A histogram with a density curve is displayed along with the specification limits and a Quantile-Quantile Plot for the specified distribution. Lower-, upper and total fraction of nonconforming entities are calculated. Box-Cox Transformations are supported as well as the calculation of Anderson Darling Test Statistics.

Usage

pcr(
  x,
  distribution = "normal",
  lsl,
  usl,
  target,
  boxcox = FALSE,
  lambda = c(-5, 5),
  main,
  xlim,
  grouping = NULL,
  std.dev = NULL,
  conf.level = 0.9973002,
  bounds.lty = 3,
  bounds.col = "red",
  col.fill = "lightblue",
  col.border = "black",
  col.curve = "red",
  plot = TRUE,
  ADtest = TRUE
)

Arguments

Details

Distribution fitting is delegated to the function FitDistr from this package, as well as the calculation of lambda for the Box-Cox Transformation. p-values for the Anderson-Darling Test are reported for the most important distributions.

The process capability indices are calculated as follows:

• cpk: minimum of cpK and cpL.

• pt: total fraction nonconforming.

• pu: upper fraction nonconforming.

• pl: lower fraction nonconforming.

• cp: process capability index.

• cpkL: lower process capability index.

• cpkU: upper process capability index.

• cpk: minimum process capability index.

For a Box-Cox transformation, a data vector with positive values is needed to estimate an optimal value of lambda for the Box-Cox power transformation of the values. The Box-Cox power transformation is used to bring the distribution of the data vector closer to normality. Estimation of the optimal lambda is delegated to the function boxcox from the MASS package. The Box-Cox transformation has the form y(\lambda) = \frac{y^\lambda - 1}{\lambda} for \lambda \neq 0, and y(\lambda) = \log(y) for \lambda = 0. The function boxcox computes the profile log-likelihoods for a range of values of the parameter lambda. The function boxcox.lambda returns the value of lambda with the maximum profile log-likelihood.

In case no specification limits are given, lsl and usl are calculated to support a process capability index of 1.

Value

The function returns a list with the following components:

The function pcr returns a list with lambda, cp, cpl, cpu, ppt, ppl, ppu, A, usl, lsl, target, asTest, plot.

Examples

set.seed(1234)
data <- rnorm(20, mean = 20)
pcr(data, "normal", lsl = 17, usl = 23)

set.seed(1234)
weib <- rweibull(20, shape = 2, scale = 8)
pcr(weib, "weibull", usl = 20)

pgamma3: The gamma Distribution (3 Parameter)

Description

Density function, distribution function, and quantile function for the Gamma distribution.

Usage

pgamma3(q, shape, scale, threshold)

Arguments

Details

The Gamma distribution with scale parameter alpha, shape parameter c, and threshold parameter zeta has a density given by:

f(x) = \frac{c}{\alpha}\left(\frac{x-\zeta}{\alpha}\right)^{c-1}\exp\left(-\left(\frac{x-\zeta}{\alpha}\right)^c\right)

The cumulative distribution function is given by:

F(x) = 1 - \exp\left(-\left(\frac{x-\zeta}{\alpha}\right)^c\right)

Value

dgamma3 gives the density, pgamma3 gives the distribution function, and qgamma3 gives the quantile function.

Examples

dgamma3(x = 1, scale = 1, shape = 5, threshold = 0)
temp <- pgamma3(q = 1, scale = 1, shape = 5, threshold = 0)
temp
qgamma3(p = temp, scale = 1, shape = 5, threshold = 0)

plnorm3: The Lognormal Distribution (3 Parameter)

Description

Density function, distribution function, and quantile function for the Lognormal distribution.

Usage

plnorm3(q, meanlog, sdlog, threshold)

Arguments

Details

The Lognormal distribution with meanlog parameter zeta, sdlog parameter sigma, and threshold parameter theta has a density given by:

f(x) = \frac{1}{\sqrt{2\pi}\sigma(x-\theta)}\exp\left(-\frac{(\log(x-\theta)-\zeta)^2}{2\sigma^2}\right)

The cumulative distribution function is given by:

F(x) = \Phi\left(\frac{\log(x-\theta)-\zeta}{\sigma}\right)

where \Phi is the cumulative distribution function of the standard normal distribution.

Value

dlnorm3 gives the density, plnorm3 gives the distribution function, and qlnorm3 gives the quantile function.

Examples

dlnorm3(x = 2, meanlog = 0, sdlog = 1/8, threshold = 1)
temp <- plnorm3(q = 2, meanlog = 0, sdlog = 1/8, threshold = 1)
temp
qlnorm3(p = temp, meanlog = 0, sdlog = 1/8, threshold = 1)

ppPlot: Probability Plots for various distributions

Description

Function ppPlot creates a Probability plot of the values in x including a line.

Usage

ppPlot(
  x,
  distribution,
  confbounds = TRUE,
  alpha,
  probs,
  main,
  xlab,
  ylab,
  xlim,
  ylim,
  border = "red",
  bounds.col = "black",
  bounds.lty = 1,
  start,
  showPlot = TRUE,
  axis.y.right = FALSE,
  bw.theme = FALSE
)

Arguments

Details

Distribution fitting is performed using the FitDistr function from this package. For the computation of the confidence bounds, the variance of the quantiles is estimated using the delta method, which involves the estimation of the observed Fisher Information matrix as well as the gradient of the CDF of the fitted distribution. Where possible, those values are replaced by their normal approximation.

Value

The function ppPlot returns an invisible list containing:

See Also

qqPlot, FitDistr.

Examples

set.seed(123)
ppPlot(rnorm(20, mean=90, sd=5), "normal",alpha=0.30)
ppPlot(rcauchy(100), "cauchy")
ppPlot(rweibull(50, shape = 1, scale = 1), "weibull")
ppPlot(rlogis(50), "logistic")
ppPlot(rlnorm(50) , "log-normal")
ppPlot(rbeta(10, 0.7, 1.5),"beta")
ppPlot(rpois(20,3), "poisson")
ppPlot(rchisq(20, 10),"chi-squared")
ppPlot(rgeom(20, prob = 1/4), "geometric")
ppPlot(rnbinom(n = 20, size = 3, prob = 0.2), "negative binomial")
ppPlot(rf(20, df1 = 10, df2 = 20), "f")

print_adtest: Test Statistics

Description

Function to show adtest.

Usage

print_adtest(x, digits = 4, quote = TRUE, prefix = "", ...)

Arguments

Value

The function returns a summary of Anderson Darling Test

Examples

data <- rnorm(20, mean = 20)
pcr1<-pcr(data, "normal", lsl = 17, usl = 23, plot = FALSE)
print_adtest(pcr1$adTest)

pweibull3: The Weibull Distribution (3 Parameter)

Description

Density function, distribution function, and quantile function for the Weibull distribution with a threshold parameter.

Usage

pweibull3(q, shape, scale, threshold)

Arguments

Details

The Weibull distribution with the scale parameter alpha, shape parameter c, and threshold parameter zeta has a density function given by:

f(x) = \frac{c}{\alpha} \left(\frac{x - \zeta}{\alpha}\right)^{c-1} \exp\left(-\left(\frac{x - \zeta}{\alpha}\right)^c\right)

The cumulative distribution function is given by:

F(x) = 1 - \exp\left(-\left(\frac{x - \zeta}{\alpha}\right)^c\right)

Value

dweibull3 returns the density, pweibull3 returns the distribution function, and qweibull3 returns the quantile function for the Weibull distribution with a threshold.

Examples

dweibull3(x = 1, scale = 1, shape = 5, threshold = 0)
temp <- pweibull3(q = 1, scale = 1, shape = 5, threshold = 0)
temp
qweibull3(p = temp, scale = 1, shape = 5, threshold = 0)

qgamma3: The gamma Distribution (3 Parameter)

Description

Density function, distribution function, and quantile function for the Gamma distribution.

Usage

qgamma3(p, shape, scale, threshold, ...)

Arguments

Details

The Gamma distribution with scale parameter alpha, shape parameter c, and threshold parameter zeta has a density given by:

f(x) = \frac{c}{\alpha}\left(\frac{x-\zeta}{\alpha}\right)^{c-1}\exp\left(-\left(\frac{x-\zeta}{\alpha}\right)^c\right)

The cumulative distribution function is given by:

F(x) = 1 - \exp\left(-\left(\frac{x-\zeta}{\alpha}\right)^c\right)

Value

dgamma3 gives the density, pgamma3 gives the distribution function, and qgamma3 gives the quantile function.

Examples

dgamma3(x = 1, scale = 1, shape = 5, threshold = 0)
temp <- pgamma3(q = 1, scale = 1, shape = 5, threshold = 0)
temp
qgamma3(p = temp, scale = 1, shape = 5, threshold = 0)

qlnorm3: The Lognormal Distribution (3 Parameter)

Description

Density function, distribution function, and quantile function for the Lognormal distribution.

Usage

qlnorm3(p, meanlog, sdlog, threshold, ...)

Arguments

Details

The Lognormal distribution with meanlog parameter zeta, sdlog parameter sigma, and threshold parameter theta has a density given by:

f(x) = \frac{1}{\sqrt{2\pi}\sigma(x-\theta)}\exp\left(-\frac{(\log(x-\theta)-\zeta)^2}{2\sigma^2}\right)

The cumulative distribution function is given by:

F(x) = \Phi\left(\frac{\log(x-\theta)-\zeta}{\sigma}\right)

where \Phi is the cumulative distribution function of the standard normal distribution.

Value

dlnorm3 gives the density, plnorm3 gives the distribution function, and qlnorm3 gives the quantile function.

Examples

dlnorm3(x = 2, meanlog = 0, sdlog = 1/8, threshold = 1)
temp <- plnorm3(q = 2, meanlog = 0, sdlog = 1/8, threshold = 1)
temp
qlnorm3(p = temp, meanlog = 0, sdlog = 1/8, threshold = 1)

qqPlot: Quantile-Quantile Plots for various distributions

Description

Function qqPlot creates a QQ plot of the values in x including a line which passes through the first and third quartiles.

Usage

qqPlot(
  x,
  y,
  confbounds = TRUE,
  alpha,
  main,
  xlab,
  ylab,
  xlim,
  ylim,
  border = "red",
  bounds.col = "black",
  bounds.lty = 1,
  start,
  showPlot = TRUE,
  axis.y.right = FALSE,
  bw.theme = FALSE
)

Arguments

Details

Distribution fitting is performed using the FitDistr function from this package. For the computation of the confidence bounds, the variance of the quantiles is estimated using the delta method, which involves the estimation of the observed Fisher Information matrix as well as the gradient of the CDF of the fitted distribution. Where possible, those values are replaced by their normal approximation.

Value

The function qqPlot returns an invisible list containing:

See Also

ppPlot, FitDistr.

Examples

set.seed(123)
qqPlot(rnorm(20, mean=90, sd=5), "normal",alpha=0.30)
qqPlot(rcauchy(100), "cauchy")
qqPlot(rweibull(50, shape = 1, scale = 1), "weibull")
qqPlot(rlogis(50), "logistic")
qqPlot(rlnorm(50) , "log-normal")
qqPlot(rbeta(10, 0.7, 1.5),"beta")
qqPlot(rpois(20,3), "poisson")
qqPlot(rchisq(20, 10),"chi-squared")
qqPlot(rgeom(20, prob = 1/4), "geometric")
qqPlot(rnbinom(n = 20, size = 3, prob = 0.2), "negative binomial")
qqPlot(rf(20, df1 = 10, df2 = 20), "f")

qweibull3: The Weibull Distribution (3 Parameter)

Description

Density function, distribution function, and quantile function for the Weibull distribution with a threshold parameter.

Usage

qweibull3(p, shape, scale, threshold, ...)

Arguments

Details

The Weibull distribution with the scale parameter alpha, shape parameter c, and threshold parameter zeta has a density function given by:

f(x) = \frac{c}{\alpha} \left(\frac{x - \zeta}{\alpha}\right)^{c-1} \exp\left(-\left(\frac{x - \zeta}{\alpha}\right)^c\right)

The cumulative distribution function is given by:

F(x) = 1 - \exp\left(-\left(\frac{x - \zeta}{\alpha}\right)^c\right)

Value

dweibull3 returns the density, pweibull3 returns the distribution function, and qweibull3 returns the quantile function for the Weibull distribution with a threshold.

Examples

dweibull3(x = 1, scale = 1, shape = 5, threshold = 0)
temp <- pweibull3(q = 1, scale = 1, shape = 5, threshold = 0)
temp
qweibull3(p = temp, scale = 1, shape = 5, threshold = 0)

randomize: Randomization

Description

Function to do randomize the run order of factorial designs.

Usage

randomize(fdo, random.seed = 93275938, so = FALSE)

Arguments

Value

An object of class facDesign.c with the run order randomized.

Examples

dfrac <- fracDesign(k = 3)
randomize(dfrac)

rsmChoose: Choosing a response surface design from a table

Description

Designs displayed are central composite designs with orthogonal blocking and near rotatability. The function allows users to choose a design by clicking with the mouse into the appropriate field.

Usage

rsmChoose()

Value

Returns an object of class facDesign.c.

See Also

fracChoose, rsmDesign

Examples

rsmChoose()

rsmDesign: Generate a response surface design.

Description

Generates a response surface design containing a cube, centerCube, star, and centerStar portion.

Usage

rsmDesign(
  k = 3,
  p = 0,
  alpha = "rotatable",
  blocks = 1,
  cc = 1,
  cs = 1,
  fp = 1,
  sp = 1,
  faceCentered = FALSE
)

Arguments

Details

Generated designs consist of a cube, centerCube, star, and centerStar portion. The replication structure can be set with the parameters cc (centerCube), cs (centerStar), fp (factorialPoints), and sp (starPoints).

Value

The function returns an object of class facDesign.c.

See Also

facDesign, fracDesign, fracChoose, pbDesign, rsmChoose

Examples

# Example 1: Central composite design for 2 factors with 2 blocks, alpha = 1.41,
# 5 centerpoints in the cube portion and 3 centerpoints in the star portion:
rsmDesign(k = 2, blocks = 2, alpha = sqrt(2), cc = 5, cs = 3)

# Example 2: Central composite design with both, orthogonality and near rotatability
rsmDesign(k = 2, blocks = 2, alpha = "both")

# Example 3: Central composite design with:
# 2 centerpoints in the factorial portion of the design (i.e., 2)
# 1 centerpoint in the star portion of the design (i.e., 1)
# 2 replications per factorial point (i.e., 2^3*2 = 16)
# 3 replications per star point (i.e., 3*2*3 = 18)
# Makes a total of 37 factor combinations
rsdo = rsmDesign(k = 3, blocks = 1, alpha = 2, cc = 2, cs = 1, fp = 2, sp = 3)

simProc: Simulated Process

Description

This is a function to simulate a black box process for teaching the use of designed experiments. The optimal factor settings can be found using a sequential assembly strategy i.e. apply a 2^k factorial design first, calculate the path of the steepest ascent, again apply a 2^k factorial design and augment a star portion to find the optimal factor settings. Of course, other strategies are possible.

Usage

simProc(x1, x2, x3, noise = TRUE)

Arguments

Value

simProc returns a numeric value within the range [0,1].

Examples

simProc(120, 140, 1)
simProc(120, 220, 1)
simProc(160, 140, 1)

snPlot: Signal-to-Noise-Ratio Plots

Description

Creates a Signal-to-Noise Ratio plot for designs of type taguchiDesign.c with at least two replicates.

Usage

snPlot(object, type = "nominal", factors, fun = mean, response = NULL,
       points = FALSE, classic = FALSE, lty, xlab, ylab,
       main, ylim, l.col, p.col, ld.col, pch)

Arguments

Details

The Signal-to-Noise Ratio (SNR) is calculated based on the type specified:

• `nominal`:

  SN = 10 \cdot log(mean(y) / var(y))

• `smaller`:

  SN = -10 \cdot log((1 / n) \cdot sum(y^2))

• `larger`:

  SN = -10 \cdot log((1 / n) \cdot sum(1 / y^2))

Signal-to-Noise Ratio plots are used to estimate the effects of individual factors and to judge the variance and validity of results from an effect plot.

Value

An invisible data.frame containing all the single Signal-to-Noise Ratios.

Examples

tdo <- taguchiDesign("L9_3", replicates = 3)
tdo$.response(rnorm(27))
snPlot(tdo, points = TRUE, l.col = 2, p.col = 2, ld.col = 2, pch = 16, lty = 3)

starDesign: Axial Design

Description

starDesign is a function to create the star portion of a response surface design. The starDesign function can be used to create a star portion of a response surface design for a sequential assembly strategy. One can either specify k and p and alpha and cs and cc OR simply simply pass an object of class facDesign.c to the data. In the latter an object of class facDesign.c otherwise a list containing the axial runs and centerpoints is returned.

Usage

starDesign(
  k,
  p = 0,
  alpha = c("both", "rotatable", "orthogonal"),
  cs,
  cc,
  data
)

Arguments

Value

starDesign returns a facDesign.c object if an object of class facDesign.c is given or a list containing entries for axial runs and center points in the cube and the star portion of a design.

See Also

facDesign, fracDesign, rsmDesign, mixDesign

Examples

# Example 1: sequential assembly
# Factorial design with one center point in the cube portion
fdo = facDesign(k = 3, centerCube = 1)
# Set the response via generic response method
fdo$.response(1:9)
# Sequential assembly of a response surface design (rsd)
rsd = starDesign(data = fdo)

# Example 2: Returning a list of star point designs
starDesign(k = 3, cc = 2, cs = 2, alpha = "orthogonal")
starDesign(k = 3, cc = 2, cs = 2, alpha = "rotatable")
starDesign(k = 3, cc = 2, cs = 2, alpha = "both")

steepAscent: Steepest Ascent

Description

steepAscent is a method to calculate the steepest ascent for a facDesign.c object.

Usage

steepAscent(factors, response, size = 0.2, steps = 5, data)

Arguments

Value

steepAscent returns an object of class steepAscent.c.

See Also

optimum, desirability

Examples

# Example 1
fdo = facDesign(k = 2, centerCube = 5)
fdo$lows(c(170, 150))
fdo$highs(c(230, 250))
fdo$names(c("temperature", "time"))
fdo$unit(c("C", "minutes"))
yield = c(32.79, 24.07, 48.94, 52.49, 38.89, 48.29, 29.68, 46.5, 44.15)
fdo$.response(yield)
fdo$summary()

sao = steepAscent(factors = c("B", "A"), response = "yield", size = 1,
                  data = fdo)

steepAscent-class: Class 'steepAscent'

Description

The steepAscent.c class represents a steepest ascent algorithm in a factorial design context. This class is used for optimizing designs based on iterative improvements.

Public fields

Methods

Public methods

• steepAscent.c$.response()

• steepAscent.c$get()

• steepAscent.c$as.data.frame()

• steepAscent.c$print()

• steepAscent.c$plot()

• steepAscent.c$clone()

Method .response()

Get and set the 'response' values in an object of class 'steepAscent.c'.

Usage

steepAscent.c$.response(value)

Arguments

Method get()

Access specific elements in the design matrix or response data of the object.

Usage

steepAscent.c$get(i, j)

Arguments

Method as.data.frame()

Convert the object to a data frame.

Usage

steepAscent.c$as.data.frame()

Method print()

Print the details of the object.

Usage

steepAscent.c$print()

Method plot()

Plot the results of the steepest ascent procedure for an object of class 'steepAscent.c'.

Usage

steepAscent.c$plot(main, xlab, ylab, l.col, p.col, line.type, point.shape)

Arguments

Method clone()

The objects of this class are cloneable with this method.

Usage

steepAscent.c$clone(deep = FALSE)

Arguments

See Also

steepAscent, desirability.c, optimum

summaryFits: Fit Summary

Description

Function to provide an overview of fitted linear models for objects of class facDesign.c.

Usage

summaryFits(fdo, lmFit = TRUE, curvTest = TRUE)

Arguments

Value

A summary output of the fitted linear models, which may include the linear fits, curvature tests, and original fit values, depending on the input parameters.

Examples

dfac <- facDesign(k = 3)
dfac$.response(data.frame(y = rnorm(8), y2 = rnorm(8)))
dfac$set.fits(lm(y ~ A + B , data = dfac$as.data.frame()))
dfac$set.fits(lm(y2 ~ A + C, data = dfac$as.data.frame()))
summaryFits(dfac)

taguchiChoose: Taguchi Designs

Description

Shows a matrix of possible taguchi designs

Usage

taguchiChoose(
  factors1 = 0,
  factors2 = 0,
  level1 = 0,
  level2 = 0,
  ia = 0,
  col = 2,
  randomize = TRUE,
  replicates = 1
)

Arguments

Details

taguchiChoose returns possible taguchi designs. Specifying the number of factor1 factors with level1 levels (factors1 = 2, level1 = 3 means 2 factors with 3 factor levels) and factor2 factors with level2 levels and desired interactions one or more taguchi designs are suggested. If all parameters are set to 0, a matrix of possible taguchi designs is shown.

Value

taguchiChoose returns an object of class taguchiDesign.

See Also

• facDesign: for 2^k factorial designs.

• rsmDesign: for response surface designs.

• fracDesign: for fractional factorial design.

• gageRRDesign: for gage designs.

Examples

tdo1 <- taguchiChoose()
tdo1 <- taguchiChoose(factors1 = 3, level1 = 2)

taguchiDesign: Taguchi Designs

Description

Function to create a taguchi design.

Usage

taguchiDesign(design, randomize = TRUE, replicates = 1)

Arguments

Details

An overview of possible taguchi designs is possible with taguchiChoose.

Value

A taguchiDesign returns an object of class taguchiDesign.

See Also

• facDesign: for 2^k factorial designs.

• rsmDesign: for response surface designs.

• fracDesign: for fractional factorial design.

• pbDesign: for response surface designs.

• gageRRDesign: for gage designs.

Examples

tdo <- taguchiDesign("L9_3")
tdo$values(list(A = c("material 1", "material 2", "material 3"), B = c(29, 30, 35)))
tdo$names(c("Factor 1", "Factor 2", "Factor 3", "Factor 4"))
tdo$.response(rnorm(9))
tdo$summary()

taguchiDesign

Description

An R6 class representing a Taguchi experimental design.

Public fields

Methods

Public methods

• taguchiDesign.c$values()

• taguchiDesign.c$units()

• taguchiDesign.c$.factors()

• taguchiDesign.c$names()

• taguchiDesign.c$as.data.frame()

• taguchiDesign.c$print()

• taguchiDesign.c$.response()

• taguchiDesign.c$.nfp()

• taguchiDesign.c$summary()

• taguchiDesign.c$effectPlot()

• taguchiDesign.c$identity()

• taguchiDesign.c$clone()

Method values()

Get and set the values for an object of class taguchiDesign.

Usage

taguchiDesign.c$values(value)

Arguments

Method units()

Get and set the units for an object of class taguchiDesign.

Usage

taguchiDesign.c$units(value)

Arguments

Method .factors()

Get and set the factors in an object of class taguchiDesign.

Usage

taguchiDesign.c$.factors(value)

Arguments

Method names()

Get and set the names in an object of class taguchiDesign.

Usage

taguchiDesign.c$names(value)

Arguments

Method as.data.frame()

Return a data frame with the information of the object taguchiDesign.c.

Usage

taguchiDesign.c$as.data.frame()

Method print()

Methods for function print in Package base.

Usage

taguchiDesign.c$print()

Method .response()

Get and set the the response in an object of class taguchiDesign.

Usage

taguchiDesign.c$.response(value)

Arguments

Method .nfp()

Prints a summary of the factors attributes including their low, high, name, unit, and type.

Usage

taguchiDesign.c$.nfp()

Method summary()

Methods for function summary in Package base.

Usage

taguchiDesign.c$summary()

Method effectPlot()

Plots the effects of factors on the response variables.

Usage

taguchiDesign.c$effectPlot(
  factors,
  fun = mean,
  response = NULL,
  points = FALSE,
  l.col,
  p.col,
  ld.col,
  lty,
  xlab,
  ylab,
  main,
  ylim,
  pch
)

Arguments

Examples

tdo = taguchiDesign("L9_3")
tdo$.response(rnorm(9))
tdo$effectPlot(points = TRUE, pch = 16, lty = 3)

Method identity()

Calculates the alias table for a fractional factorial design and prints an easy to read summary of the defining relations such as 'I = ABCD' for a standard 2^(4-1) factorial design.

Usage

taguchiDesign.c$identity()

Method clone()

The objects of this class are cloneable with this method.

Usage

taguchiDesign.c$clone(deep = FALSE)

Arguments

Examples

## ------------------------------------------------
## Method `taguchiDesign.c$effectPlot`
## ------------------------------------------------

tdo = taguchiDesign("L9_3")
tdo$.response(rnorm(9))
tdo$effectPlot(points = TRUE, pch = 16, lty = 3)

taguchiFactor

Description

An R6 class representing a factor in a Taguchi design.

Public fields

Methods

Public methods

• taguchiFactor$attributes()

• taguchiFactor$.values()

• taguchiFactor$.unit()

• taguchiFactor$names()

• taguchiFactor$clone()

Method attributes()

Get the attributes of the factor.

Usage

taguchiFactor$attributes()

Method .values()

Get and set the values for the factors in an object of class taguchiFactor.

Usage

taguchiFactor$.values(value)

Arguments

Method .unit()

Get and set the units for the factors in an object of class taguchiFactor.

Usage

taguchiFactor$.unit(value)

Arguments

Method names()

Get and set the names in an object of class taguchiFactor.

Usage

taguchiFactor$names(value)

Arguments

Method clone()

The objects of this class are cloneable with this method.

Usage

taguchiFactor$clone(deep = FALSE)

Arguments

wirePlot: 3D Plot

Description

Creates a wireframe diagram for an object of class facDesign.c.

Usage

wirePlot(
  x,
  y,
  z,
  data = NULL,
  xlim,
  ylim,
  zlim,
  main,
  xlab,
  ylab,
  sub,
  sub.a = TRUE,
  zlab,
  form = "fit",
  col = "Rainbow",
  steps,
  fun,
  plot = TRUE,
  show.scale = TRUE,
  n.scene = "scene"
)

Arguments