clr_tests: Conditional Likelihood Ratio Tests (CLR)

In iarm: Item Analysis in Rasch Models

Conditional Likelihood Ratio Tests (CLR)

Description

The conditional likelihood ratio tests compare item parameters in low and high score groups for an overall test of homogeneity, and in groups defined by the levels of exogenous factors for tests of no differential item functioning (DIF).

Usage

clr_tests(dat.items, dat.exo = NULL, model = c("RM", "PCM"))

Arguments

dat.items	A data frame with the responses to the items.
dat.exo	A single factor or a data frame consisting of one or more exogenous factor variables.
model	If model="RM" a Rasch model will be fitted, if model="PCM" a partial credit model for polytomous items is used.

Value

matrix with test statistics, df and p values.

Author(s)

Marianne Mueller

References

Andersen, E.B. (1973). A goodness of fit test for the Rasch model. Psychometrika, 38, 123-140.

Examples

#CLR overall test and test of  no DIF for agegrp and sex
clr_tests(amts[,4:13],amts[,2:3])

iarm documentation built on Aug. 27, 2022, 5:06 p.m.