Compute an information criterion

Description

Given the fitted parameter values for a log-linear model, compute an information criterion.

Usage

1
get.IC(predictors, ddat, ic, beta)

Arguments

predictors

A character vector of predictors of the form "c1", "c2" for main effects, or "c12" for an interaction. The predictors to be used in a log-linear model. For example, "c1", "c2" for main effects, or "c12" for an interaction.

ddat

A data frame that is the design matrix for a log-linear model.

ic

The information criterion to be computed. Currently the AIC, AICc, BIC, BICpi are implemented.

beta

The vector of log-linear coefficients that were previously estimated.

Details

Computes the conditional multinomial likelihood and uses it to compute the specified information criterion

Value

The value of the information criterion

Author(s)

Zach Kurtz

References

Thesis of Zach Kurtz (2014), Carnegie Mellon University, Statistics

Anderson DR and Burnham KP (1999). "Understanding information criteria for selection among capture-recapture or ring recovery models." Bird Study, 46(S1), pp. S14-S21.


Questions? Problems? Suggestions? or email at ian@mutexlabs.com.

Please suggest features or report bugs with the GitHub issue tracker.

All documentation is copyright its authors; we didn't write any of that.