SSN (version 1.1.7)

getPreds: Extract Predictions with associated standard errors.

Description

This function extracts predictions and standard errors from objects of class 'glmssn.predict' or 'influenceSSN'. Predictions are extracted for unobserved locations, while cross-validation predictions are extracted for observed locations.

Usage

getPreds(x, pred.type = "cv")

Arguments

x

an object of class predict.glmssn or influenceSSN-class

pred.type

prediction type, either "pred" or "cv". The "pred" option indicates that a 'glmssn.predict' object is being accessed and a text file containing predictions and standard errors for the predictions is exported. When the "cv" option is used, objects of class influenceSSN are accessed and cross-validation predictions and standard errors are exported.

Value

getPreds returns a matrix containing the point identifier (pid), the predictions, and the standard errors for the predictions.

See Also

predict, influenceSSN-class

Examples

library(SSN)
# NOT RUN
#mf04p <- importSSN(system.file("lsndata/MiddleFork04.ssn",
#  package = "SSN"), predpts = "pred1km", o.write = TRUE)
#  use SpatialStreamNetwork object mf04p that was already created
data(mf04p)
# for examples, copy MiddleFork04.ssn directory to R's temporary directory
copyLSN2temp()
#make sure mf04p has the correct path, will vary for each users installation
mf04p <- updatePath(mf04p, paste0(tempdir(),'/MiddleFork04.ssn'))

# get some model fits stored as data objects
data(modelFits)
#NOT RUN use this one
#fitSp <- glmssn(Summer_mn ~ ELEV_DEM + netID,
#    ssn.object = mf04p, EstMeth = "REML", family = "Gaussian",
#    CorModels = c("Exponential.tailup","Exponential.taildown",
#    "Exponential.Euclid"), addfunccol = "afvArea")
#Update the path in fitSp, will vary for each users installation
fitSp$ssn.object <- updatePath(fitSp$ssn.object, 
  paste0(tempdir(),'/MiddleFork04.ssn'))

# Extract predictions and standard errors for the prediction sites
# make sure the distance matrix is there
createDistMat(mf04p, predpts = "pred1km", o.write = TRUE)
#create predictions
fitSpPred <- predict(fitSp, predpointsID = "pred1km")
class(fitSpPred)
fitSpgetPreds <- getPreds(fitSpPred, pred.type = "pred")
head(fitSpgetPreds)

# Extract cross-validation predictions for the observed sites in two ways:
fitSpRes <- residuals(fitSp)
class(fitSpRes)

# Extract from the influenceSSN class object
fitSpResGetCV <- getPreds(fitSpRes, pred.type = "cv")
head(fitSpResGetCV)

# Extract from the glmssn.predict class object
fitSpResGetCV2 <- getPreds(fitSpPred, pred.type = "cv")
# These values are identical
identical(fitSpResGetCV,fitSpResGetCV) ## TRUE