Class Notes (808,108)
Canada (493,014)
POL101Y1 (1,114)
Lecture 4

QR Lecture 4.pdf

4 Pages
Unlock Document

University of Toronto St. George
Political Science
Michael Painter- Main

Research Design - Experiments and Content Analysis - Follow along with slides Content analysis audiences Sources = who wrote it content = message audience = intended cohort common technique = non-verbal cues effect = outcomes, relationships Each foci adopts specific tests of meaning (manifest or latent) Reliability inter-code reliability when we're trying to measure a message, we have to make sure to be accurate in our measurement How do we amplify our confidence in our measurements? Inter-coder reliability Done by getting people to experience something individually and coming to the same conclusion as everyone else Multiple individuals coding same material how often do they come to similar conclusions gives confidence that there is a consistency of agreement Content analysis in practice - blogs and deliberative democracy Looking at political blogs, trying to measure bias, etc. Methodologically rigours? Not a word about inter-coder reliability - left to assume that authors coded themselves, no test to see if others came to the same conclusion during measurement Surveys If you have a sample size of 100 people and they start trying to make generalisations, doesn't mean that it's too low to make predictions. 100 people isn't too low for a sample size, don't make that argument. 1000, 2000 is pretty good. Sources Lot of places online hold data for anyone to grab and analyse World values survey, freedom house Canadian electoral surveys - check in with people before after and during elections global barometer surveys cora - holding company for different surveys that have been commissioned Surveys often secondary we don't commission our own surveys, especially if they're on a massive scale takes time and money to do it properly most of the time we rely on those aforementioned sites as data that's already been collected for us to analyse If we do secondary, how can we have control over what's asked? We have to deal with it. You have to make sure that the questions in the survey are really tapping into what we're researching We have to be cautious about using secondary data, but it's not so bad. It shouldnt be a carte blanche for criticism Surveys have a benefit of quickly and easily grabbing patterns Surveys vs experiments experiment is about control and vacuum Causal relationships - much more difficult using surveys (compared to experiments) Difficulty revolves around controlling multiple causes unable to be accounted for, or difficult to take into account controlling is done after the fact through statistical testing Surveys are good at generalising to a population, experiments instead focus on demonstration Random sampling is paramount We need to make sure that our sample is random to ensure reliable data Should be representative of the population - best way is random - every single person has the same chance of being selected in reality, this is very difficult - there are ways of cracking it and massaging it to bias simple random sampling - as easy a draw - pick names from a hat systematic random sampling - assign everyone in group a number, pick a random number, and pick that person (say 10) + pick every 10th person in the group for a full sample cluster sampling - select groups from a population, then randomly choose people from the extracted groups Stratified sampling - ensures a good measurement of underrepresented groups in population Importance of random sampling 1936 US election - FDR vs Alf Landon Huge sample size, but predicted the winning result wrong by 20% What happened? They didn't apply random sampling. This was a convenien
More Less

Related notes for POL101Y1

Log In


Don't have an account?

Join OneClass

Access over 10 million pages of study
documents for 1.3 million courses.

Sign up

Join to view


By registering, I agree to the Terms and Privacy Policies
Already have an account?
Just a few more details

So we can recommend you notes for your school.

Reset Password

Please enter below the email address you registered with and we will send you a link to reset your password.

Add your courses

Get notes from the top students in your class.