Experimental Methods Soc 201
Popular in Social Psychology
Popular in Sociology
verified elite notetaker
This 3 page Class Notes was uploaded by Julia Caine on Thursday September 15, 2016. The Class Notes belongs to Soc 201 at New York University taught by Blaine Robbins in Fall 2016. Since its upload, it has received 14 views. For similar materials see Social Psychology in Sociology at New York University.
Reviews for Experimental Methods
Report this Material
What is Karma?
Karma is the currency of StudySoup.
You can buy or earn more Karma at anytime and redeem it for class notes, study guides, flashcards, and more!
Date Created: 09/15/16
Experimental Methods What methods are available to social psychologists? o Survey Ideally random samples Problem- people are self-reporting o Archival research o Experiments are most common “Gold standard” Experiments o Background concepts Variable Characteristic that you can count, measure, or label Must have possibility of two or more conditions Independent variable Hypothesized cause of variation in dependent variable Also called predictor Dependent variable Hypothesized effect of variation in independent variable Also called outcome Extraneous variable Outside variables that could affect independent variable Also called confounder Want relationship between independent and extraneous variables to equal zero Manipulation Researcher can turn on or off independent variable Condition Two sets of guidelines that differ Treatment and control groups Random assignment Subjects are randomly given one of conditions Create equivalent groups o Larger groups means more equality If people self-select you introduce bias o Definition When an independent variable is manipulated by researcher to observe a hypothesized effect in the dependent variable while holding extraneous variables constant via random assignment Want to carefully control environment o Examples Medical research Need placebo Food preservation Status in academia People can write bad papers and still be accepted if they have high status o y=β +0 β 1ε1 Outcome=model+error Example SAT SCORE= β +WHETHER OR NOT THEY TOOK SAT PREP 0 COURSE*β +ε1 o Can predict person’s score before and after taking prep course When COV(X , ε1 = 0, X is c1usally identified and β is 1 unbiased o y=β +0 β 1X1β +2 2 +ε3 3 Introducing more independent variable SAT=β +0OURSE*β +MOTI1ATION*β +SES*β +ε2 3 COV(COURSE, MOTIVATION)≠0 COV(COURSE, SES)≠0 If we don’t measure MOTIVATION and SES, it goes in error term o Β is upwardly biased because COV(COURSE, ε)≠0 1 which means that COURSE=X β +1O1IVATION*β +SES*β 2 3 o Manipulation You must manipulate independent variable Create 2 or more conditions One condition studies are not experiments o Merely demonstrations o Advantages Control Artificiality Easily replicated “Keep it simple, stupid” o Disadvantages Demand effect Self-presentation effect o Subjects believe they know the hypothesis being tested and try to produce those results “Hawthorne” effect o People naturally behave differently when they know they’re being observed Reverse-demand effect o Subjects believe they know the hypothesis being tested and try to produce the opposite results Experimenter effect o Experimenter might unconsciously give hints to treatment group Can offset these with o Double-blind treatment Neither the subjects nor the person giving the experiment knows which group is treatment and which is placebo o Deception Try to make subjects think the test is testing one hypothesis when it is actually testing a different one External validity Generalizing info about one group to different groups o Usually study undergrad students Not good at macro-processes
Are you sure you want to buy this material for
You're already Subscribed!
Looks like you've already subscribed to StudySoup, you won't need to purchase another subscription to get this material. To access this material simply click 'View Full Document'