The hardware and bandwidth for this mirror is donated by METANET, the Webhosting and Full Service-Cloud Provider.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]metanet.ch.

Type: Package
Title: Detection of Differential Item Functioning (DIF) in Rasch Models by Boosting Techniques
Version: 0.4
Date: 2025-07-22
Imports: mboost, penalized, stabs
Maintainer: Gunther Schauberger <gunther.schauberger@tum.de>
Description: Performs detection of Differential Item Functioning using the method DIFboost as proposed by Schauberger and Tutz (2016) <doi:10.1111/bmsp.12060>.
License: GPL-2
LazyLoad: yes
NeedsCompilation: no
Packaged: 2025-07-22 11:04:02 UTC; ge29weh
Author: Gunther Schauberger [aut, cre]
Repository: CRAN
Date/Publication: 2025-07-22 11:50:15 UTC

DIFboost

Description

A package to perform DIFboost, a method to detect DIF (Differential Item Functioning) in Rasch Models. It can handle settings with many covariates and also metric covariates simultaneously. The method is described in Tutz and Schauberger (2015). Model/variable selection is performed using stability selection.

Details

The method assumes the DIFmodel from Tutz and Schauberger (2015) where boosting is used for DIF detection. Computation is based on the functions gamboost and stabsel.

Author(s)

Gunther Schauberger
gunther.schauberger@tum
https://www.sg.tum.de/epidemiologie/team/schauberger/

References

Schauberger, Gunther and Tutz, Gerhard (2016): Detection of Differential Item Functioning in Rasch Models by Boosting Techniques, British Journal of Mathematical and Statistical Psychology, 69(1), 80 - 103

See Also

DIFboost, print.DIFboost

Examples

## Not run: 
data(simul.data)

Y <- simul.data[,1:10]
X <- simul.data[,11:13]

m1 <- DIFboost(Y = Y, X = X) 
print(m1)

## End(Not run)

Detection of Differential Item Functioning (DIF) in Rasch Models by Boosting Techniques

Description

A function to perform DIFboost, a method to detect DIF (Differential Item Functioning) in Rasch Models. It can handle settings with many covariates and also metric covariates simultaneously. The method is described in Tutz and Schauberger (2015). Model/variable selection is performed using stability selection.

Usage

DIFboost(Y, X, mstop = 400, trace = TRUE, cutoff = 0.9, 
         B = 500, mc.cores = 1, q = 0.6 * I)

Arguments

Y

Data frame (one row per person, one column per item) containing response. May only contain 0 or 1.

X

Data frame (one row per person, one column per covariate) containing covariates. Has to be standardized.

mstop

Number of boosting iterations maximally performed in one iteration of the stability selection.

trace

Should the trace of the single boosting steps be printed?

cutoff

Cutoff value for stability selection.

B

Number of subsamples used for stability selection.

mc.cores

Number of cores for parallelized stability selection. For windows machines, parallelization is not possible.

q

Maximum number of base learner to be included in the boosting algorithm for one subsample in stability selection. By default set to 60 percent of the total number of items.

Details

The method assumes the DIFmodel from Tutz and Schauberger (2015) where boosting is used for DIF detection. Computation is based on the functions gamboost and stabsel.

Value

model

Model from inital gamboost fit

dif.mat

Estimates of the item-specific parameter estimates, with zeros for non-DIF items

coefficients

coefficient vector with all estimates from refitted model

theta

Estimated person abilities

beta

Estimated item difficulties

gamma

Estimated item-specific parameters

P

Number of (valid) persons

I

Number of items

names.y

Names of the items

names.x

Names of the covariates

design.matrix

Design matrix for refitted model

PFER

upper bound for the per-family error rate. For details see stabsel.

lin.pred

linear predictor from refitted model

DIF.items

Which items have been detected to be DIF items?

ref.item

Reference item

phat

selection probabilities for single base learners in stability selection. For details see stabsel

cutoff

cutoff value used for stability selection

Author(s)

Gunther Schauberger
gunther.schauberger@tum
https://www.sg.tum.de/epidemiologie/team/schauberger/

References

Schauberger, Gunther and Tutz, Gerhard (2016): Detection of Differential Item Functioning in Rasch Models by Boosting Techniques, British Journal of Mathematical and Statistical Psychology, 69(1), 80 - 103

See Also

print.DIFboost, gamboost, stabsel

Examples

## Not run: 
data(simul.data)

Y <- simul.data[,1:10]
X <- simul.data[,11:13]

m1 <- DIFboost(Y = Y, X = X) 
print(m1)

## End(Not run)

Print function for DIFboost

Description

Prints the most important output of a DIFboost object.

Usage

## S3 method for class 'DIFboost'
print(x, ...)

Arguments

x

DIFboost object, created by DIFboost

...

Further arguments to be passed to the print function.

Author(s)

Gunther Schauberger
gunther.schauberger@tum
https://www.sg.tum.de/epidemiologie/team/schauberger/

References

Schauberger, Gunther and Tutz, Gerhard (2016): Detection of Differential Item Functioning in Rasch Models by Boosting Techniques, British Journal of Mathematical and Statistical Psychology, 69(1), 80 - 103

See Also

DIFboost

Examples

## Not run: 
data(simul.data)

Y <- simul.data[,1:10]
X <- simul.data[,11:13]

m1 <- DIFboost(Y = Y, X = X) 
print(m1)

## End(Not run)

Simulated data set

Description

Simulated data set with 100 persons, 10 items and 3 (standardized) covariates. Items 1, 2 and 3 are DIF items.

Usage

data(simul.data)

Format

Item1

Item 1, DIF item

Item2

Item 2, DIF item

Item3

Item 3, DIF item

Item4

Item 4, non-DIF item

Item5

Item 5, non-DIF item

Item6

Item 6, non-DIF item

Item7

Item 7, non-DIF item

Item8

Item 8, non-DIF item

Item9

Item 9, non-DIF item

Item10

Item 10, non-DIF item

CovBin1

Binary covariate (standardized)

CovBin2

Binary covariate (standardized)

CovMet

Metric covariate (standardized)

Author(s)

Gunther Schauberger
gunther.schauberger@tum
https://www.sg.tum.de/epidemiologie/team/schauberger/

References

Schauberger, Gunther and Tutz, Gerhard (2016): Detection of Differential Item Functioning in Rasch Models by Boosting Techniques, British Journal of Mathematical and Statistical Psychology, 69(1), 80 - 103

See Also

DIFboost, print.DIFboost

Examples

## Not run: 
data(simul.data)

Y <- simul.data[,1:10]
X <- simul.data[,11:13]

m1 <- DIFboost(Y = Y, X = X) 
print(m1)

## End(Not run)

These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.