POL222H1 Lecture Notes - Lecture 4: Internal Validity, Clientelism, Confounding
Document Summary
Obstacles to establishing causality: reverse causality and simultaneous relationship, confounding variables an apparent relationship between x and y may not represent a true relationship. Research designs: strategies that researcher can use to empirically test whether x causes y: experiments, observational studies. It has been found that voters who had been exposed to a negative political advertisement were more likely to vote. In the second one, they already watched the positive one: so we are not controlling for a confounding factor, this person has already been exposed to a positive. Ideological bias of news: ne(cid:449)s media"s reputatio(cid:374) actual bas in news, he has a sample of 256 undergrad students, dependent variable: ideological score of the news shown on a 50 point scale (0=most liberal, 25=neutral, 50=most conservative) Internal validity: the degree of confidence in the causal conclusion drawn from analysis, external validity, degree of confidence in generalizability of the causal conclusion drawn from the analysis.
