TAM (version 0.04-43)

tam.pv: Plausible Value Imputation

Description

Plausible value imputation for objects of the classes tam and tam.mml (Adams & Wu, 2007).

Usage

tam.pv(tamobj, nplausible = 10, ntheta = 2000, normal.approx = FALSE, 
    samp.regr = FALSE , np.adj=4 )

Arguments

tamobj

Object of class tam or tam.mml

nplausible

Number of plausible values to be drawn

ntheta

Number of ability nodes for plausible value imputation. Note that in this function ability nodes are simulated for the whole sample, not for every person (contrary to the software ConQuest).

normal.approx

Should individual posterior distributions be approximated by a normal distribution? The default is TRUE. In this case, the number of ability nodes ntheta can be substantially smaller than 2000, say 200 or 500.

samp.regr

Should regression coefficients be fixed in the imputation or also sampled from their posterior distribution? The default is FALSE.

np.adj

This parameter defines the spread of the random theta values for drawing plausible values when normal.approx=FALSE. If $s_{EAP}$ denotes the standard deviation of the posterior distribution of theta (in the one-dimensional c

...

Further arguments to be passed

Value

• A list with following entries:
• pv
  A data frame containing a person identifier (pid) and plausible values denoted by PVxx.Dimyy which is the xxth plausible value of dimension yy.
• hwt
  Individual posterior distribution evaluated at the ability grid theta
• hwt1
  Cumulated individual posterior distribution
• theta
  Simulated ability nodes

References

Adams, R. J., & Wu, M. L. (2007). The mixed-coefficients multinomial logit model. A generalized form of the Rasch model. In M. von Davier & C. H. Carstensen (Eds.): Multivariate and mixture distribution Rasch models: Extensions and applications (pp. 55-76). New York: Springer.

Examples

data(sim.rasch)
# estimate Rasch model
mod <- tam.mml(sim.rasch)
# draw 5 plausible values (without a normality
# assumption of the posterior) and 2000 ability nodes
pv1 <- tam.pv( mod , nplausible=5 , ntheta=2000 )