TAM (version 2.4-9)

IRT.itemfit.tam: RMSEA Item Fit Statistics for TAM Objects

Description

Computes the RMSEA item fit statistic for fitted objects in the TAM package, see CDM::IRT.itemfit and CDM::itemfit.rmsea.

Usage

# S3 method for tam.mml
IRT.itemfit(object, method="rmsea", …)
# S3 method for tam.mml.2pl
IRT.itemfit(object, method="rmsea", …)
# S3 method for tam.mml.mfr
IRT.itemfit(object, method="rmsea", …)
# S3 method for tam.mml.3pl
IRT.itemfit(object, method="rmsea", …)

Arguments

object

Object of class tam.mml, tam.mml.2pl, tam.mml.mfr or tam.mml.3pl.

method

Requested method for item fit calculation. Currently, only the RMSEA fit statistic (CDM::itemfit.rmsea) can be used.

…

Further arguments to be passed.

See Also

CDM::IRT.itemfit, CDM::itemfit.rmsea

Examples

# NOT RUN {
#############################################################################
# EXAMPLE 1: RMSEA item fit statistic data.read
#############################################################################

library(sirt)
data(data.read,package="sirt")
dat <- data.read

#*** fit 1PL model
mod1 <- TAM::tam.mml( dat )
summary(mod1)

#*** fit 2PL model
mod2 <- TAM::tam.mml.2pl( dat )
summary(mod2)

#*** assess RMSEA item fit
fmod1 <- IRT.itemfit(mod1)
fmod2 <- IRT.itemfit(mod2)
# summary of fit statistics
summary( fmod1$rmsea )
summary( fmod2$rmsea )

#############################################################################
# EXAMPLE 2: Simulated 2PL data and fit of 1PL model
#############################################################################

set.seed(987)
N <- 1000    # 1000 persons
I <- 10      # 10 items
# define item difficulties and item slopes
b <- seq(-2,2,len=I)
a <- rep(1,I)
a[c(3,8)] <- c( 1.7 , .4 )
# simulate 2PL data
dat <- sirt::sim.raschtype( theta=rnorm(N) , b = b , fixed.a = a)

# fit 1PL model
mod <- TAM::tam.mml( dat )

# RMSEA item fit
fmod <- IRT.itemfit(mod)
round( fmod$rmsea , 3 )
# }