SpatioTemporal (version 1.1.9.1)

mesa.data.raw: Data used in the examples

Description

The raw data that was used to create the mesa.model structures.

The data structure contains raw data from the MESA Air project. The example below describes how to create the mesa.model structure from raw data.

Format

The structure contains observations, temporal trends, locations, geographic covariates, and spatio-temporal covariates. The data is stored as a list with elements:

X

A data.frame containing names, locations, and (geographic) covariates for all the (observation) locations.

obs

A time-by-location matrix for the observed data, missing data marked as NA

lax.conc.1500

A time-by-location matrix of a spatio-temporal covariate based on output from Caline3QHC.

References

M. A. Cohen, S. D. Adar, R. W. Allen, E. Avol, C. L. Curl, T. Gould, D. Hardie, A. Ho, P. Kinney, T. V. Larson, P. D. Sampson, L. Sheppard, K. D. Stukovsky, S. S. Swan, L. S. Liu, J. D. Kaufman. (2009) Approach to Estimating Participant Pollutant Exposures in the Multi-Ethnic Study of Atherosclerosis and Air Pollution (MESA Air). Environmental Science & Technology: 43(13), 4687-4693.

See Also

createSTdata for creation of STdata objects.

Other data matrix: SVDmiss, SVDsmooth, createDataMatrix, estimateBetaFields

Other example data: MCMC.mesa.model, est.cv.mesa, est.mesa.model, mesa.model, pred.mesa.model

Examples

# NOT RUN {
##load the data
data(mesa.data.raw)

##extract matrix of observations (missing marked by NA)
obs.mat <- mesa.data.raw$obs
head(obs.mat)

##optionally observations can be given as a data.frame
obs <- data.frame(obs=c(obs.mat),
                  date=rep(rownames(obs.mat), dim(obs.mat)[2]),
                  ID=rep(colnames(obs.mat), each=dim(obs.mat)[1]))
##force date-format
obs$date <- as.Date(obs$date)

##drop unobserved
obs <- obs[!is.na(obs$obs),,drop=FALSE]

##create a 3D-array for the spatio-temporal covariate
ST <- array(mesa.data.raw$lax.conc.1500, dim =
            c(dim(mesa.data.raw$lax.conc.1500),1))
dimnames(ST) <- list(rownames(mesa.data.raw$lax.conc),
                     colnames(mesa.data.raw$lax.conc),
                     "lax.conc.1500")
##or use a list of matrices
ST.list <- list(lax.conc.1500=mesa.data.raw$lax.conc.1500)

###########################
## create STdata object ##
###########################
##Create the data-object
mesa.data <- createSTdata(obs.mat, mesa.data.raw$X, n.basis=2,
                          SpatioTemporal=ST)
mesa.data.2 <- createSTdata(obs, mesa.data.raw$X, n.basis=2,
                            SpatioTemporal=ST.list)

##This should yield equal structures,
##which are also the same as data(mesa.data)
all.equal(mesa.data, mesa.data.2)

###########################
## create STmodel object ##
###########################
##define land-use covariates, for intercept and trends
LUR <- list(~log10.m.to.a1+s2000.pop.div.10000+km.to.coast,
  ~km.to.coast, ~km.to.coast)
##and covariance model
cov.beta <- list(covf="exp", nugget=FALSE)
cov.nu <- list(covf="exp", nugget=~type, random.effect=FALSE)
##which locations to use
locations <- list(coords=c("x","y"), long.lat=c("long","lat"), others="type")
##create object
mesa.model <- createSTmodel(mesa.data, LUR=LUR, ST="lax.conc.1500",
                            cov.beta=cov.beta, cov.nu=cov.nu,
                            locations=locations)

##This should be the same as the data in data(mesa.model)
# }