Perform one step of iterative proportional updating

C++ routines to invoke a single iteration of the Iterative proportional updating (IPU) scheme. Targets and classes are assumed to be one dimensional in the ipf_step functions. combine_factors aggregates several vectors of type factor into a single one to allow multidimensional ipu-steps. See examples.

ipf_step_ref(w, classes, targets)

ipf_step(w, classes, targets)

ipf_step_f(w, classes, targets)

combine_factors(dat, targets)

Arguments

w	a numeric vector of weights. All entries should be positive.
classes	a factor variable. Must have the same length as w.
targets	key figure to target with the ipu scheme. A numeric verctor of the same length as levels(classes). This can also be a table produced by xtabs. See examples.
dat	a data.frame containing the factor variables to be combined.

Details

ipf_step returns the adjusted weights. ipf_step_ref does the same, but updates w by reference rather than returning. ipf_step_f returns a multiplicator: adjusted weights divided by unadjusted weights. combine_factors is designed to make ipf_step work with contingency tables produced by xtabs.

Examples

############# one-dimensional ipu ##############

## create random data
nobs <- 10
classLabels <- letters[1:3]
dat = data.frame(
  weight = exp(rnorm(nobs)),
  household = factor(sample(classLabels, nobs, replace = TRUE))
)
dat
#>       weight household
#> 1  0.6640834         c
#> 2  5.1397911         b
#> 3  1.2591308         a
#> 4  0.6516811         c
#> 5  0.9171716         b
#> 6  2.1896192         a
#> 7  0.4860760         c
#> 8  3.0053915         c
#> 9  5.6514550         a
#> 10 0.5395121         c

## create targets (same lenght as classLabels!)
targets <- 3:5

## calculate weights
new_weight <- ipf_step(dat$weight, dat$household, targets)
cbind(dat, new_weight)
#>       weight household new_weight
#> 1  0.6640834         c  0.6210167
#> 2  5.1397911         b  3.3943026
#> 3  1.2591308         a  0.4150887
#> 4  0.6516811         c  0.6094186
#> 5  0.9171716         b  0.6056974
#> 6  2.1896192         a  0.7218362
#> 7  0.4860760         c  0.4545532
#> 8  3.0053915         c  2.8104875
#> 9  5.6514550         a  1.8630751
#> 10 0.5395121         c  0.5045239

## check solution
xtabs(new_weight ~ dat$household)
#> dat$household
#> a b c 
#> 3 4 5 

## calculate weights "by reference"
ipf_step_ref(dat$weight, dat$household, targets)
dat
#>       weight household
#> 1  0.6210167         c
#> 2  3.3943026         b
#> 3  0.4150887         a
#> 4  0.6094186         c
#> 5  0.6056974         b
#> 6  0.7218362         a
#> 7  0.4545532         c
#> 8  2.8104875         c
#> 9  1.8630751         a
#> 10 0.5045239         c

############# multidimensional ipu ##############

## load data
factors <- c("time", "sex", "smoker", "day")
tips <- data.frame(sex=c("Female","Male","Male"), day=c("Sun","Mon","Tue"),
time=c("Dinner","Lunch","Lunch"), smoker=c("No","Yes","No"))
tips <- tips[factors]

## combine factors
con <- xtabs(~., tips)
cf <- combine_factors(tips, con)
cbind(tips, cf)[sample(nrow(tips), 10, replace = TRUE),]
#>       time    sex smoker day cf
#> 1   Dinner Female     No Sun  9
#> 2    Lunch   Male    Yes Mon  8
#> 2.1  Lunch   Male    Yes Mon  8
#> 3    Lunch   Male     No Tue 20
#> 2.2  Lunch   Male    Yes Mon  8
#> 1.1 Dinner Female     No Sun  9
#> 2.3  Lunch   Male    Yes Mon  8
#> 1.2 Dinner Female     No Sun  9
#> 3.1  Lunch   Male     No Tue 20
#> 2.4  Lunch   Male    Yes Mon  8

## adjust weights
weight <- rnorm(nrow(tips)) + 5
adjusted_weight <- ipf_step(weight, cf, con)

## check outputs
con2 <- xtabs(adjusted_weight ~ ., data = tips)
sum((con - con2)^2)
#> [1] 0