SpatioTemporal (version 1.1.2)

simulate.STmodel: Simulate Data from the Spatio-Temporal Model

Description

Data is simulated for the space-time locations in object using the parameters in x.

Usage

## S3 method for class 'STmodel':
simulate(object, nsim = 1,
    seed = NULL, x, nugget.unobs = 0, ...)

Arguments

object

A STmodel object to perform unconditional simulation from.

nsim

Number of replicates to simulate.

seed

if !=NULL used in a call to set.seed, allowing for replicatable simulation studies.

x

Parameters to use when simulating the data; both regression and covariance parameters must be given, see loglikeSTgetPars.

nugget.unobs

Value of nugget at unonserved locations, either a scalar or a vector with one element per unobserved site.

...

Additional parameters for set.seed

Value

• A list containing:
• param
  Parameters used in the simulation, i.e. x.
• B
  The simulated beta fields in a (number of locations) - by - (number of temporal trends) - by - (number of replicates) array.
• X
  The simulated spatio-temporal fields in a (number of timepoints) - by - (number of locations) - by - (number of replicates) array. Row and column names indicate the time and locations for each point.
• obs
  A list with one element per replicate, containing the simulated observations extracted at space-time locations matching those in object$obs. To replace the observations with the i:th simulated values do: object$obs <- res$obs[[i]].

See Also

Other STmodel methods: createSTmodel, c.STmodel, estimateCV.STmodel, estimate.STmodel, MCMC.STmodel, plot.STdata, plot.STmodel, predictCV.STmodel, predict.STmodel, print.STmodel, print.summary.STmodel, summary.STmodel

Examples

##load the data
data(mesa.data)
data(mesa.model)
data(est.mesa.model)

##Get estimated parameters
x <- coef(est.mesa.model)$par

##Simulate 5 replicates from these parameters
sim.data <- simulate(mesa.model, nsim=5, x=x)

##compute average beta fields
beta <- calc.mu.B(mesa.model$LUR, loglikeSTgetPars(x, mesa.model)$alpha)

##plot the simulated observations as a function of time
par(mfrow=c(2,2), mar=c(4,4,.5,.5))
plot(sim.data$obs[[1]]$date, sim.data$obs[[1]]$obs,
     type="n", ylab="obs", xlab="Date")
for(i in 1:5){
  points(sim.data$obs[[i]]$date, sim.data$obs[[i]]$obs, col=i)
}
##and the latent beta-fields
for(i in 1:3){
  plot(sim.data$B[,i,1], ylim=range(sim.data$B[,i,]), type="n",
       xlab="loc", ylab=paste("beta",colnames(sim.data$B)[i]))
  for(j in 1:5){
    points(sim.data$B[,i,j], col=j)
  }
  lines( beta[,i], col="grey")
}

###########################################
## A case with some unobserved locations ##
###########################################
##keep only observations from the AQS sites
I.aqs <- mesa.data$covars$ID[ mesa.data$covars$type=="AQS"]
mesa.data$obs <- mesa.data$obs[ mesa.data$obs$ID %in% I.aqs,]

##create a new model object
mesa.model <- createSTmodel(mesa.data, LUR = mesa.model$LUR.list)

##simulate some replicates for this object
sim.data2 <- simulate(mesa.model, nsim=1, x=x)

##The new object now only contains simulated observations for the AQS sites
table( sim.data2$obs[[1]]$ID )
##while the other two contain all locations
table( sim.data$obs[[1]]$ID )