Model Selection Mixtures of Multinomials

Assess the number of components in a mixture of multinomials model using the Akaike's information criterion (AIC), Schwartz's Bayesian information criterion (BIC), Bozdogan's consistent AIC (CAIC), and Integrated Completed Likelihood (ICL).

Usage

multmixmodel.sel(y, comps = NULL, ...)

Arguments

y

Either An nxp matrix of data (multinomial counts), where n is the sample size and p is the number of multinomial bins, or the output of the makemultdata function. It is not necessary that all of the rows contain the same number of multinomial trials (i.e., the row sums of y need not be identical).

comps

Vector containing the numbers of components to consider. If NULL, this is set to be 1:(max possible), where (max possible) is floor((m+1)/2) and m is the minimum row sum of y.

...

Arguments passed to multmixEM that control convergence of the underlying EM algorithm.

Value

multmixmodel.sel returns a table summarizing the AIC, BIC, CAIC, ICL, and log-likelihood values along with the winner (the number with the lowest aforementioned values).

See also

compCDF, makemultdata, multmixEM

Examples

##Data generated using the multinomial cutpoint method.

set.seed(100)
x <- matrix(rpois(70, 6), 10, 7) 
x.new <- makemultdata(x, cuts = 5)
multmixmodel.sel(x.new$y, comps = c(1,2), epsilon = 1e-03)
#> number of iterations= 5 
#>                1         2 Winner
#> AIC    -16.87652 -17.04152      1
#> BIC    -17.02782 -17.49540      1
#> CAIC   -17.52782 -18.99540      1
#> ICL    -17.02782 -16.82665      2
#> Loglik -15.87652 -14.04152      2