# Generation of smaller regions given an existing spatial variable and a table. This function allows to manipulate an object of class `simPopObj` in a way that a new variable containing smaller regions within an already existing broader region is generated. The distribution of the smaller region within the broader region is respected. ```r simInitSpatial( simPopObj, additional, region, tspatialP = NULL, tspatialHH = NULL, eps = 0.05, maxIter = 100, nr_cpus = NULL, seed = 1, verbose = FALSE ) ``` ## Arguments - `simPopObj`: an object of class `simPopObj`. - `additional`: a character vector of length one holding the variable name of the variable containing smaller geographical units. This variable name must be available as a column in input argument `tspatial`. - `region`: a character vector of length one holding the variable name of the broader region. This variable must be available in the input `tspatial` as well as in the sample and population slots of input `simPopObj`. - `tspatialP`: a data.frame (or data.table) containing three columns. The broader region (with the variable name being the same as in input `region`, the smaller geographical units (with the variable name being the same as in input `additional`) and a third column containing a numeric vector holding counts of persons. This argument or tspatialHH has to be provided. - `tspatialHH`: a data.frame (or data.table) containing three columns. The broader region (with the variable name being the same as in input `region`, the smaller geographical units (with the variable name being the same as in input `additional`) and a third column containing a numeric vector holding counts of households. This argument or tspatialP has to be provided. - `eps`: relative deviation of person counts if person and household counts are provided - `maxIter`: maximum number of iteration for adjustment if person and household counts are provided - `nr_cpus`: if specified, an integer number defining the number of cpus that should be used for parallel processing. - `seed`: optional; an integer value to be used as the seed of the random number generator, or an integer vector containing the state of the random number generator to be restored. - `verbose`: TRUE/FALSE if some information should be shown during the process ## Returns An object of class `simPopObj` with an additional variable in the synthetic population slot. ## Details The distributional information must be contained in an input table that holds combinations of characteristics of the broader region and the smaller regions as well as population counts (which may be available from a census). ## Examples ```r library(data.table) data(eusilcS) data(eusilcP) library(data.table) # no districts are available in the population, so we have to generate those # we randomly assign districts within "region" in the eusilc population data # each hh has the same district simulate_districts <- function(inp) { hhid <- "hid" region <- "region" a <- inp[!duplicated(inp[,hhid]),c(hhid, region)] spl <- split(a, a[,region]) regions <- unique(inp[,region]) tmpres <- lapply(1:length(spl), function(x) { codes <- paste(x, 1:sample(3:9,1), sep="") spl[[x]]$district <- sample(codes, nrow(spl[[x]]), replace=TRUE) spl[[x]] }) tmpres <- do.call("rbind", tmpres) tmpres <- tmpres[,-c(2)] out <- merge(inp, tmpres, by.x=c(hhid), by.y=hhid, all.x=TRUE) invisible(out) } eusilcP <- data.table(simulate_districts(eusilcP)) # we generate the input table using the broad region (variable 'region') # and the districts, we have generated before. #Generate table with household counts by district tabHH <- eusilcP[!duplicated(hid),.(Freq=.N),by=.(db040=region,district)] setkey(tabHH,db040,district) #Generate table with person counts by district tabP <- eusilcP[,.(Freq=.N),by=.(db040=region,district)] setkey(tabP,db040,district) # we generate a synthetic population setnames(eusilcP,"region","db040") setnames(eusilcP,"hid","db030") inp <- specifyInput(data=eusilcP, hhid="db030", hhsize="hsize", strata="db040",population=TRUE) ## Not run: # use only HH counts simPopObj <- simStructure(data=inp, method="direct", basicHHvars=c("age", "gender")) simPopObj1 <- simInitSpatial(simPopObj, additional="district", region="db040", tspatialHH=tabHH, tspatialP=NULL, nr_cpus=1) # use only P counts simPopObj <- simStructure(data=inp, method="direct", basicHHvars=c("age", "gender")) simPopObj2 <- simInitSpatial(simPopObj, additional="district", region="db040", tspatialHH=NULL, tspatialP=tabP, nr_cpus = 1) # use P and HH counts simPopObj <- simStructure(data=inp, method="direct", basicHHvars=c("age", "gender")) simPopObj3 <- simInitSpatial(simPopObj, additional="district", region="db040", tspatialHH=tabHH, tspatialP=tabP, nr_cpus = 1) ## End(Not run) ``` ## References M. Templ, B. Meindl, A. Kowarik, A. Alfons, O. Dupriez (2017) Simulation of Synthetic Populations for Survey Data Considering Auxiliary Information. **Journal of Statistical Survey**, 79 (10), 1--38. tools:::Rd_expr_doi("10.18637/jss.v079.i10") ## Author(s) Bernhard Meindl and Alexander Kowarik

simInitSpatial function