POLS 3650 Lecture Notes - Lecture 15: Chi-Squared Distribution, Statistical Significance

• School: University of Guelph
• Department: Political Science
• Course: POLS 3650
• Professor: Edward Koning

Document Summary

Measures of asso(cid:272)iatio(cid:374) for (cid:374)o(cid:373)i(cid:374)al varia(cid:271)les: (cid:272)ra(cid:373)er"s a(cid:374)d la(cid:373)(cid:271)da. Bivariate analysis of nominal variables: as any bivariate investigation of sample data, the analysis of the relationship between two nominal variables proceeds through five steps, formulate hypotheses, visualization: crosstabs, calculate measure of association. I(cid:374) this (cid:272)lass, we will (cid:272)o(cid:374)sider two differe(cid:374)t(cid:373)easures of asso(cid:272)iatio(cid:374): cra(cid:373)er"s v and lambda: conduct test of statistical significance: chi square. Conclusion: the relationship between religion and vote intention is moderately strong and statistically significant. We want to investigate whether men are more likely to be engaged in demonstrations that women. H1= men are more likely to protest in demonstrations than women. Ho = men are no more likely to protest in demnostrations than women. Conclusion: there does not seem to be a significant relationship between gender and participation in protests. We cannot safely reject ho and even if there were a relationship, it would be a very weak one.