Model Selection in Mixtures of Normals with Repeated Measures

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

Usage

repnormmixmodel.sel(x, k = 2, ...)

Arguments

x

An mxn matrix of observations. The rows correspond to the repeated measures and the columns correspond to the subject.

k

The maximum number of components to assess.

...

Additional arguments passed to repnormmixEM.

Value

repnormmixmodel.sel returns a matrix of the AIC, BIC, CAIC, and ICL values along with the winner (i.e., the highest value given by the model selection criterion) for a mixture of normals with repeated measures.

See also

repnormmixEM

References

Biernacki, C., Celeux, G., and Govaert, G. (2000). Assessing a Mixture Model for Clustering with the Integrated Completed Likelihood. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(7):719-725.

Bozdogan, H. (1987). Model Selection and Akaike's Information Criterion (AIC): The General Theory and its Analytical Extensions. Psychometrika, 52:345-370.

Examples

## Assessing the number of components for the water-level task data set.

data(Waterdata)
water<-t(as.matrix(Waterdata[,3:10]))
set.seed(100)
out <- repnormmixmodel.sel(water, k = 3, epsilon = 5e-01)
#> number of iterations= 14 
#> number of iterations= 16 
out
#>              1         2         3 Winner
#> AIC  -14703.91 -13122.20 -12754.66      3
#> BIC  -14703.99 -13122.32 -12754.86      3
#> CAIC -14704.99 -13123.82 -12757.36      3
#> ICL  -14703.99 -13121.64 -12753.78      3