simulate.blim: Simulate Responses from Basic Local Independence Models...

In pks: Probabilistic Knowledge Structures

Simulate Responses from Basic Local Independence Models (BLIMs)

Description

Simulates response frequencies from the distribution corresponding to a fitted blim model object. Alternatively, if sufficient information is provided, it generates response frequencies from scratch (see examples).

Usage

## S3 method for class 'blim'
simulate(object, nsim = 1, seed = NULL, ...,
         method = c("bernoulli", "multinomial"), zeropad = FALSE)

Arguments

object	an object of class blim, typically the result of a call to blim.
nsim	currently not used.
seed	currently not used.
...	further arguments passed to or from other methods. None are used in this method.
method	bernoulli (default) or multinomial sampling.
zeropad	logical, if TRUE non-sampled response patterns have a frequency of zero, else (default) they are omitted.

Details

Bernoulli sampling: Responses are simulated in two steps: First, a knowledge state is drawn with probability P.K. Second, responses are generated by applying rbinom with probabilities computed from the model object's beta and eta components. Faster with a large number of items.

Multinomial sampling: The probability of all response patterns is computed from the model object's parameters, and response frequencies are obtained from rmultinom. Faster with few items but a large number of respondents.

Value

A named vector of frequencies of response patterns.

See Also

blim, endm.

Examples

data(DoignonFalmagne7)
 
m1 <- blim(DoignonFalmagne7$K, DoignonFalmagne7$N.R)
simulate(m1)
simulate(m1, method = "multinomial", zeropad = TRUE)

## Parametric bootstrap for the BLIM
disc <- replicate(200, blim(m1$K, simulate(m1))$discrepancy)

hist(disc, col = "lightgray", border = "white", freq = FALSE, breaks = 20,
     main = "BLIM parametric bootstrap", xlim = c(.05, .3))
abline(v = m1$discrepancy, lty = 2)

## Parameter recovery for the SLM
m0 <- list( P.K = getSlmPK( g = rep(.8, 5),
                            K = DoignonFalmagne7$K,
                           Ko = getKFringe(DoignonFalmagne7$K)),
           beta = rep(.1, 5),
            eta = rep(.1, 5),
              K = DoignonFalmagne7$K,
         ntotal = 800)
class(m0) <- c("slm", "blim")

pars <- replicate(20, coef(slm(m0$K, simulate(m0), method = "ML")))
boxplot(t(pars), horizontal = TRUE, las = 1,
        main = "SLM parameter recovery")

## See ?endm for further examples.

pks documentation built on Sept. 16, 2026, 9:09 a.m.