Seminar Details

Seminar Details


Friday

Feb 25

3:30 pm

Classification by Opinion-Changing Behavior: A Mixture Model Approach

Jennifer Hill (Joint with CSSS)

Seminar

Harvard University - Department of Statistics

Popular theories in political science regarding opinion-changing behavior postulate existence of one or both of two broad categories of people: those who hold their opinions over time; and those that hold no solid opinion and, when asked to make a choice, do so seemingly at random. This study explores evidence for a third category: durable changers. This group of people will change their opinion in a rational, informed manner, after being exposed to new information. Survey data collected at four time points over nearly two years tracks Swiss citizens' readiness to support pollution-reduction policies. The data is incomplete in the 3rd and 4th years. Finite mixture models allow estimation of the percentage in the population of each category for each question. Specific behaviors attributable to each of the three groups can be explicitly measured. Data Augmentation is implemented to fit the models. Posterior predictive checks and Bayes factors are used to explore model fit. Results provide evidence for existence of the durable-changer group.