SO5032: Lab Materials
Table of Contents
1 Week 11 Lab: Multinomial Logistic Regression
1.1 Multinomial logistic regression
Load this BHPS excerpt:
use http://teaching.sociology.ul.ie/so5032/bhpsqual.dta
vote has four categories. Examine bivariate
relationships between vote and some of the other variables, and then
search for a multinomial logistic regession that makes sense:
mlogit vote indvars…. It is better to have a
base category that is easily interpretable, and the default here will
use the biggest category ("Other/nationalist"). To avoid this, use the
baseoutcome(1) option, which will force category one as the
base. Use the likelihood-ratio
test for each variable, since there are three times as many parameters
as usual. Note you will need to deal with missing values.
1.1.1 Predictions
Use predict to generate predicted values (note you have
to supply one variable name to hold the prediction for each category). How often is
the most probable predicted category the same as the observed one?
1.1.2 Multinomial regression with ordinal variables
Repeat the exercise using qual as the dependent
variable. Select the variables carefully: some do not make sense for
predicting highest qualification.