GDINA: bootSE – R documentation

Become an expert in R — Interactive courses, Cheat Sheets, certificates and more!

bootSE

Calculating standard errors and variance-covariance matrix using bootstrap methods

Description

This function conducts nonparametric and parametric bootstrap to calculate standard errors of model parameters. Parametric bootstrap is only applicable to single group models.

Usage

bootSE(GDINA.obj, bootsample = 50, type = "nonparametric", randomseed = 12345)

Arguments

`GDINA.obj`	an object of class GDINA
`bootsample`	the number of bootstrap samples
`type`	type of bootstrap method. Can be `parametric` or `nonparametric`
`randomseed`	random seed for resampling

Value

itemparm.se standard errors for item probability of success in list format

delta.se standard errors for delta parameters in list format

lambda.se standard errors for structural parameters of joint attribute distribution

boot.est resample estimates

Author(s)

Wenchao Ma, The University of Alabama, wenchao.ma@ua.edu

References

Ma, W., & de la Torre, J. (2020). GDINA: An R Package for Cognitive Diagnosis Modeling. Journal of Statistical Software, 93(14), 1-26.

Examples

## Not run: 
# For illustration, only 5 resamples are run
# results are definitely not reliable

dat <- sim30GDINA$simdat
Q <- sim30GDINA$simQ
fit <- GDINA(dat = dat, Q = Q, model = "GDINA",att.dist = "higher.order")
boot.fit <- bootSE(fit,bootsample = 5,randomseed=123)
boot.fit$delta.se
boot.fit$lambda.se

## End(Not run)

GDINA

The Generalized DINA Model Framework

v2.8.0

GPL-3

Authors

Wenchao Ma [aut, cre, cph], Jimmy de la Torre [aut, cph], Miguel Sorrel [ctb], Zhehan Jiang [ctb]

Initial release

2020-05-23