addKnownMargins: add known margins/totals

In statistikat/simPop: Simulation of Complex Synthetic Data Information

add known margins/totals

Description

add known margins/totals for a combination of variables for the population to an object of class simPopObj.

Usage

addKnownMargins(inp, margins)

Arguments

inp	a simPopObj containing population and household survey data as well as optionally margins in standardized format.
margins	a data.frame containing for a combination of unique variable levels for n-variables the number of known occurences in the population. The numbers must be listed in the last column of data.frame 'margins' while the characteristics must be listed in the first 'n' columns.

Details

The function takes a data.frame containing known marginals/totals for a some variables that must exist in the population (stored in slot 'pop' of input object 'inp') and updates slot 'table' of the input object. This slot finally contains the known totals.

households are drawn from the data and new ID's are generated for the new households.

Value

an object of class simPopObj with updated slot 'table'.

Author(s)

Bernhard Meindl

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. \Sexpr[results=rd]{tools:::Rd_expr_doi("10.18637/jss.v079.i10")}

Examples

data(eusilcS)
data(eusilcP)
## Not run: 
## approx. 20 seconds computation time
inp <- specifyInput(data=eusilcS, hhid="db030", hhsize="hsize", strata="db040", weight="db090")
inp <- simStructure(data=inp, method="direct", basicHHvars=c("age", "rb090"))
inp <- simCategorical(inp, additional=c("pl030", "pb220a"), method="multinom",nr_cpus=1)

margins <- as.data.frame(
  xtabs(rep(1, nrow(eusilcP)) ~ eusilcP$region + eusilcP$gender + eusilcP$citizenship))
colnames(margins) <- c("db040", "rb090", "pb220a", "freq")
inp <- addKnownMargins(inp, margins)
str(inp)

## End(Not run)

statistikat/simPop documentation built on April 13, 2025, 12:59 a.m.