SpatioTemporal (version 1.1.7)

c.STmodel: Combine Several STmodel/STdata Objects

Description

Combines several locations and covariates for several STmodel/STdata objects. Temporal trend, observations and covariance model (both spatial and spatio-temporal) are taken from the first object in the call. Any additional covariates/trends/observations not present in the first argument are dropped from the additional arguments without warning. Locations and covariates (both spatial and spatio-temporal) from additional objects are added to those in the first object.

Usage

# S3 method for STmodel
c (..., recursive = FALSE)

Arguments

...

STmodel and STdata objects to combine, the first object has to be a STmodel.

recursive

For S3 compatibility; the function will ALWAYS run recursively

Value

An updated STmodel object.

Details

For additional STdata objects the covariates are transformed according to STmodel$scale.covars of the first object, see createSTmodel.

For STmodel objects can not be combined if either has scaled covariates.

See Also

Other STdata functions: createDataMatrix, createSTdata, createSTmodel, detrendSTdata, estimateBetaFields, removeSTcovarMean, updateSTdataTrend, updateTrend, updateTrend.STdata, updateTrend.STmodel

Other STmodel methods: createSTmodel, estimate, estimate.STmodel, estimateCV, estimateCV.STmodel, MCMC, MCMC.STmodel, plot.STdata, plot.STmodel, predict.STmodel, predictCV, predictCV.STmodel, print.STmodel, print.summary.STmodel, qqnorm.predCVSTmodel, qqnorm.STdata, qqnorm.STmodel, scatterPlot.predCVSTmodel, scatterPlot.STdata, scatterPlot.STmodel, simulate.STmodel, summary.STmodel

Examples

# NOT RUN {
##load the data
data(mesa.data.raw)
##and create STdata-object
mesa.data <- createSTdata(mesa.data.raw$obs, mesa.data.raw$X, n.basis=2,
                          SpatioTemporal=mesa.data.raw["lax.conc.1500"])

##keep only observations from the AQS sites
ID.AQS <- mesa.data$covars$ID[ mesa.data$covars$type=="AQS" ]
mesa.data$obs <- mesa.data$obs[mesa.data$obs$ID %in% ID.AQS,]

##model specification
LUR <- list(~log10.m.to.a1 + s2000.pop.div.10000 + km.to.coast,
            ~km.to.coast, ~km.to.coast)
locations <- list(coords=c("x","y"), long.lat=c("long","lat"), others="type")

##create reduced model, without and with a spatio-temporal covariate.
mesa.model <- createSTmodel(mesa.data, LUR=LUR, locations=locations,
                            strip=TRUE)
mesa.model.ST <- createSTmodel(mesa.data, LUR=LUR, ST=1,
                               locations=locations, strip=TRUE)
##and non stripped version
mesa.model.full <- createSTmodel(mesa.data, LUR=LUR, ST=1,
                                 locations=locations)

##combine, this adds the missing locations
mesa.model$locations$ID
c(mesa.model, mesa.data)$locations$ID

##or we could study the summary output
print(c(mesa.model.ST, mesa.data))

##no change since we're tryin to adding existing sites
mesa.model.full$locations$ID
c(mesa.model.full, mesa.data)$locations$ID

##We can also combine two STmodels
print(c(mesa.model, mesa.model.full))
# }