Agree or disagree: are women emotionally suited for politics? A classification analysis using CART and Random Forest

There is no shortage of research exploring the link between gender stereotypes and politics. The present study attempted to contribute to this scholarship by using recursive partitioning algorithms (CART and Random Forest) to identify the most important variables in classifying whether someone agrees or disagrees that men and women differ in their emotional suitability for politics. Using data from 251 respondents to the 2022 General Social Survey (GSS), results revealed that traditional gender role ideology, as well as attitudes towards immigration and abortion, are the most important variables for classification. The implications for voting— and the underrepresentation of women in politics more generally— is a matter for future research. Caution is advised when interpreting these results, given the weaknesses of the model discussed herein.