SSN (version 1.1.17)

CrossValidationSSN: Compute Crossvalidation Values for glmssn Objects

Description

CrossValidationSSN operates on glmssn objects. The response values are removed one at a time and the estimated model is used to predict each of the removed values along with the standard errors of prediction.

Usage

CrossValidationSSN(object)

Value

Output is a data.frame with three columns, the point identifier "pid", predictions "cv.pred", and their standard errors "cv.se". The data are in the same order as the data in the glmssn object.

Arguments

object

an object of class glmssn-class

Author

Jay Ver Hoef

Details

This function removes the response values one at a time. Then it uses the estimated model to predict each of the removed values along with the standard errors of prediction.

Examples

library(SSN)
#for examples, copy MiddleFork04.ssn directory to R's temporary directory
copyLSN2temp()
# NOT RUN
# Create a SpatialStreamNetork object that also contains prediction sites
#mf04 <- importSSN(paste0(tempdir(),'/MiddleFork04.ssn', o.write = TRUE))
#use mf04 SpatialStreamNetwork object, already created
data(mf04)
#for examples only, make sure mf04p has the correct path
#if you use importSSN(), path will be correct
mf04 <- updatePath(mf04, paste0(tempdir(),'/MiddleFork04.ssn'))

## NOT RUN Distance Matrix has already been created
## createDistMat(mf04)

# The models take a little time to fit, so they are NOT RUN
# Uncomment the code to run them
# Alternatively, you can load the fitted models first to look at results
data(modelFits)

## 3 component spatial model
#fitSp <- glmssn(Summer_mn ~ ELEV_DEM + netID,
#    ssn.object = mf04, EstMeth = "REML", family = "Gaussian",
#    CorModels = c("Exponential.tailup","Exponential.taildown",
#    "Exponential.Euclid"), addfunccol = "afvArea")
#for examples only, make sure fitSp has the correct path
#if you use importSSN(), path will be correct
fitSp$ssn.object <- updatePath(fitSp$ssn.object, 
	paste0(tempdir(),'/MiddleFork04.ssn'))

fitSpCrVal <- CrossValidationSSN(fitSp)
str(fitSpCrVal)
# NOT RUN
# data are sorted by netID, then pid within netID.  This is different that
# the original data order, so get the sorted values of the response variable
# plot(fitSp$sampinfo$z, fitSpCrVal[,"cv.pred"], pch = 19)