RM.weights (version 2.0)

equating.fun: Equating scales between different application contexts.

Description

This function calibrates the measure derived by a scale applied in one context (for example, country) to the metric of a reference scale, or standard (for example, the scale applied in another country, or in the same country but through a different survey, or to any other standard). The main output is the prevalence rate in the country of interest calculated at specified thresholds along the latent trait.

Usage

equating.fun(rr1, st=NULL, tol = .35, spec.com1 = 1:8, spec.com2=1:8, 
thres = NULL, maxuniq=3, write.file=FALSE, plot=FALSE, iterative=TRUE, excl.prior1=NULL,
excl.prior2=NULL, wt.spec=NULL)

Arguments

rr1

The Rasch model fitted with the RM.w function for the country of interest.

st

Item severity parameter estimates for the reference country or the standard. The number of items for the standard may differ from the number of items of the country of interest. If left unspecified, the 2014-2016 FAO global standard for the Food Insecurity Experience Scale (FIES) is set as default.

tol

Tolerance expressed in the metric of the standard, above which items are considered unique (i.e. not contributing to the common metric between the two countries). Default is 0.35.

spec.com1

A priori numbered set of comparable items for the country of iterest to the standard. Items must be specified in the same order as they are used for the comparison.

spec.com2

A priori set of comparable items for the standard. The length of spec.com1 and spec.com2 should be the same.

thres

Thresholds (along the latent trait) corresponding to which the comparable prevalence rates of the phenomenon of interest is calculated. Default is set to the 5-th and the 8-th item of the standard specified in st.

maxuniq

A priori maximum number of unique items allowed.

write.file

Logical argument. If TRUE, a csv file with the relevant information about the equating process is created in the working directory.

plot

Logical argument. If TRUE, a pdf file with a plot of the equated item severities is produced in the working directory. Default is FALSE.

iterative

Logical argument. If TRUE, an iterative process to identify which item is unique is performed. Otherwise, unique items are specified in the arguments excl.prior1 and excl.prior2 and are taken as fixed. Default is TRUE.

excl.prior1

Numbered set of fixed unique items for the country of interest. It needs to be specified only if iterative = FALSE.

excl.prior2

Numbered set of fixed unique items for the standard. It needs to be specified only if iterative = FALSE.

wt.spec

Specified post-stratification sampling weights. If left unspecified, prevalence rates will be calculated using the weighting variable rr1$wt, otherwise the variable wt.spec will be considered.

Value

scale

Scale parameter to be applied to the metric of the country of interest to be considered equivalent to the standard.

shift

Shift parameter to be applied to the metric of the country of interest to be considered equivalent to the reference country. The standardized item parameters for the country of interest will be: b.country.st=shift+scale*b.country where b.country are estimated item severities for the country of interest.

common

Vector of characters indicating if the item in the country of interest is common compared with the standard.

prevs

Prevalence rates for the country of interest, calculated at the adjusted thresholds.

probs.rs

Probability of being bejond the adjusted thresholds calculated at each raw score.

cor.comm.items

Correlation between common items.

adj.thres

Adjusted (equated) thresholds on the country metric.

standard

The standard against which the country is compared. If the st argument is left unspecified, the 2014-2016 FAO global standard for the Food Insecurity Experience scale is returned.

See Also

prob.assign

Examples

# NOT RUN {
data(data.FAO_country1)
XX.country1 = data.FAO_country1[,1:8]
wt.country1 = data.FAO_country1$wt
rr1=RM.w(XX.country1, wt.country1)
data(data.FAO_country2)
XX.country2 = data.FAO_country2[,1:8]
wt.country2 = data.FAO_country2$wt
rr2=RM.w(XX.country2, wt.country2)
# Iterative equating
ee1=equating.fun(rr1, st=rr2$b, thres=c(-0.28, 1.85), spec.com1=c(1:8),spec.com2=c(1:8))
# Not iterative equating: fixing WORRIED unique
ee2=equating.fun(rr1, st=rr2$b, thres=c(-0.28, 1.85),spec.com1=c(1:8),
spec.com2=c(1:8), tol = .4,iterative=FALSE,excl.prior1=1,excl.prior2=1)
# Prevalence rates
ee1$prevs
ee2$prevs
# }