group.test {eba}R Documentation

Group Effects in EBA Models

Description

Tests for group effects in EBA models.

Usage

group.test(groups, A = 1:I, s = rep(1/J, J))

Arguments

groups a 3d array including one aggregated choice matrix per group
A a list of vectors consisting of the stimulus aspects; the default is 1:I, where I is the number of stimuli
s the starting vector with default 1/J for all parameters, where J is the number of parameters

Details

The five tests are all based on likelihood ratios. Overall tests a 1-parameter poisson model against a saturated poisson model. EBA.g tests an EBA group model against a saturated binomial group model, which corresponds to a goodness of fit test of the EBA group model. Group tests an EBA model for the pooled data against the EBA group model, which corresponds to testing for group differences. Effect tests an indifference model against the pooled EBA model. Imbalance tests for differences in the number of observations per pair by comparing the average sample size (1-parameter poisson model) to the actual sample sizes (saturated poisson model).

See Duineveld, Arents & King (2000) for details.

Value

tests a table displaying the likelihood ratio test statistics

References

Duineveld, C.A.A., Arents, P., & King, B.M. (2000). Log-linear modelling of paired comparison data from consumer tests. Food Quality and Preference, 11, 63–70.

See Also

OptiPt, wald.test.

Examples

data(pork)  # Is there a difference between Judge 1 and Judge 2?
groups <- array(c(apply(pork[,,1:5], 1:2, sum),
                  apply(pork[,,6:10], 1:2, sum)), c(3,3,2))
group.test(groups)

[Package eba version 1.4-1 Index]