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.

sptotal implements finite population block kriging (Ver Hoef (2008)), a geostatistical approach to predicting means and totals of count data for finite populations.

See sptotal’s Website for more information.

Installation

sptotal can be installed from CRAN

install.packages("sptotal")

or using devtools

library(devtools)
install_git("https://github.com/highamm/sptotal.git")

Simple Example

The sptotal package can be used for spatial prediction in settings where there are a finite number of sites and some of these sites were not sampled. Note that, to keep this example simple, we are simulating response values that are spatially independent. In a real example, we assume that there is some spatial dependence in the response.

set.seed(102910)
spatial_coords <- expand.grid(1:10, 1:10)
toy_df <- data.frame(xco = spatial_coords[ ,1],
yco = spatial_coords[ ,2], counts = sample(c(rpois(50, 15),
rep(NA, 50)), size = 100, replace = TRUE))

mod <- slmfit(formula = counts ~ 1, xcoordcol = "xco",
ycoordcol = "yco", data = toy_df)
summary(mod)

pred <- predict(mod)

We can look at the predictions with

pred$Pred_df[1:6, c("xco", "yco", "counts", "counts_pred_count")]

Methods and Basic Functions

sptotal Main Functions:

slmfit() fits a spatial linear model to the response on the observed/sampled sites. can be used to construct an empirical variogram of the residuals of the spatial linear model.

predict.slmfit() uses the spatial linear model fitted with slmfit() and finite population block kriging to predict counts/densities at unobserved locations. A prediction for the total count as well as a prediction variance are given by default.

For more details on how to use these functions, please see the Vignette by running

browseVignettes("sptotal")

and clicking HTML.

The methods in this package are based on the following reference:

Ver Hoef, Jay M. “Spatial methods for plot-based sampling of wildlife populations.” 15, no. 1 (2008): 3-13.

Citation

To cite this package in the literature, run the following line:

citation("sptotal")

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.