Given an internal mirt object estimate the bootstrapped standard errors. It may
be beneficial to run the computations using multi-core architecture (e.g., the parallel
package). Parameters are organized from the freely estimated values in mod2values(x)
(equality constraints will also be returned in the bootstrapped estimates).
Arguments
- x
an estimated model object
- R
number of draws to use (passed to the
boot()function)- boot.fun
a user-defined function used to extract the information from the bootstrap fitted models. Must be of the form
boot.fun(x), wherexis the bootstrap fitted model under investigation, and the return must be a numeric vector. If omitted a default function will be defined internally that returns the estimated parameters from themodobject, resulting in bootstrapped parameter estimate results- technical
technical arguments passed to estimation engine. See
mirtfor details- ...
additional arguments to be passed on to
boot(...)and mirt's estimation engine
References
Chalmers, R., P. (2012). mirt: A Multidimensional Item Response Theory Package for the R Environment. Journal of Statistical Software, 48(6), 1-29. doi:10.18637/jss.v048.i06
Author
Phil Chalmers rphilip.chalmers@gmail.com
Examples
# \donttest{
# standard
mod <- mirt(Science, 1)
booted <- boot.mirt(mod, R=20)
plot(booted)
booted
#>
#> ORDINARY NONPARAMETRIC BOOTSTRAP
#>
#>
#> Call:
#> boot.mirt(x = mod, R = 20)
#>
#>
#> Bootstrap Statistics :
#> original bias std. error
#> t1* 1.0417547 0.0342665698 0.2420681
#> t2* 4.8641542 0.1787155550 0.4737580
#> t3* 2.6399417 0.0358411673 0.3596197
#> t4* -1.4660135 -0.0379694186 0.1859787
#> t5* 1.2259618 0.0002844394 0.2089206
#> t6* 2.9240027 0.0321497871 0.2483433
#> t7* 0.9011651 -0.0263246693 0.1573818
#> t8* -2.2665647 0.0152295395 0.2412511
#> t9* 2.2933717 0.0604302858 0.6875866
#> t10* 5.2339928 0.0211130934 1.0406862
#> t11* 2.2137728 0.0129895873 0.5098426
#> t12* -1.9637062 -0.0801178395 0.4393992
#> t13* 1.0949151 0.0413075800 0.2660678
#> t14* 3.3479196 0.0323222268 0.3685192
#> t15* 0.9916289 0.0237263460 0.2245873
#> t16* -1.6882599 -0.0494895178 0.1833282
#run in parallel using snow back-end using all available cores
mod <- mirt(Science, 1)
booted <- boot.mirt(mod, parallel = 'snow', ncpus = parallel::detectCores())
booted
#>
#> ORDINARY NONPARAMETRIC BOOTSTRAP
#>
#>
#> Call:
#> boot.mirt(x = mod, parallel = "snow", ncpus = parallel::detectCores())
#>
#>
#> Bootstrap Statistics :
#> original bias std. error
#> t1* 1.0417547 0.037098798 0.2399431
#> t2* 4.8641542 0.171324713 0.4992379
#> t3* 2.6399417 0.046747648 0.2686837
#> t4* -1.4660135 -0.037984927 0.1842650
#> t5* 1.2259618 -0.011458326 0.1901372
#> t6* 2.9240027 0.021612912 0.2258715
#> t7* 0.9011651 -0.002684006 0.1472008
#> t8* -2.2665647 -0.021141768 0.2060566
#> t9* 2.2933717 0.099470109 0.6368181
#> t10* 5.2339928 0.236985335 0.9649566
#> t11* 2.2137728 0.040243580 0.4008237
#> t12* -1.9637062 -0.106392145 0.4106960
#> t13* 1.0949151 0.057835178 0.2470498
#> t14* 3.3479196 0.098303745 0.3293232
#> t15* 0.9916289 0.032866203 0.1588851
#> t16* -1.6882599 -0.057435716 0.2189009
####
# bootstrapped CIs for standardized factor loadings
boot.fun <- function(mod){
so <- summary(mod, verbose=FALSE)
as.vector(so$rotF)
}
# test to see if it works before running
boot.fun(mod)
#> [1] 0.5220496 0.5844686 0.8030199 0.5410276
# run
booted.loads <- boot.mirt(mod, boot.fun=boot.fun)
#> Warning: EM cycles terminated after 500 iterations.
#> Warning: EM cycles terminated after 500 iterations.
booted.loads
#>
#> ORDINARY NONPARAMETRIC BOOTSTRAP
#>
#>
#> Call:
#> boot.mirt(x = mod, boot.fun = boot.fun)
#>
#>
#> Bootstrap Statistics :
#> original bias std. error
#> t1* 0.5220496 0.0105477260 0.08993806
#> t2* 0.5844686 -0.0024944085 0.06369271
#> t3* 0.8030199 -0.0002012357 0.06922964
#> t4* 0.5410276 0.0083604886 0.07762805
# }