COMM 88 Lecture Notes - Lecture 12: Partial Correlation, Longitudinal Study, Dependent And Independent Variables
Comm 88 Lecture 11
May 10, 2018
Survey Research (cont.)
•Getting closer to causality…
•To help solve 3rd variable problem:
•”Partial correlation” - measure potential 3rd variable, statistically “partial out” (control for)
effects of those 3rd variables, then see if X/Y relationship still holds
•If X/Y relationship still holds, can rule out the 3rd variable as the cause
•If X/Y relationship disappears (or is reduced substantially), then the 3rd variable
explanation matters
•To help solve causal direction problem: need a longitudinal survey - “cross-lagged panel
design”
•Time 1: measure X and Y variables
•Time 2: measure X and Y variables again later for the same people
•Ex panel study: IM and adolescents’ friendships
•IV: IM use, DV: friendship quality → +r
•Compute r’s for X & Y, but across the times measured
•So, measure both variables for same people at different times, then see which “cross”
relationship holds
Experimental Research
•Purpose: to test hypotheses of cause and effect
•Goal is to establish internal validity
•Willing to sacrifice external validity
•Key elements to a true experiment
•Manipulation of IV(s)…
•Divide into different “conditions” while controlling all other variables (subjects in each
condition treated the same, etc.)
•Ex IV: new painkiller drug, half get drug, other half do not
•Examine effects on dependent variable (DV) - compare measures (mean scores) for
subjects in each condition and see if differences exist
•Ex DV: amount of perceived pain (e.g., 0-10 scale)
•Random assignment of participants (Ps) to conditions
•Everyone must have an equal chance of ending up in either condition
•Why important? Makes groups equal before manipulation
X
Y
