PSYC 2030 Study Guide - Midterm Guide: Intraclass Correlation, Correlation And Dependence, Regression Analysis

• School: York University
• Department: Psychology
• Course: PSYC 2030
• Professor: Rebecca Jubis

Document Summary

Interactions: when effect of one iv depends on level of another iv: can occur without a main effect present, can trump main effect so that the main effects are actually misleading if reported as is. Cross lagged (diagonal)panel correlation: studies correlations at several points in time with a longitudinal design, thus enforcing a -> b direction. 3rd variable problem: unknown c causes changes in both a and b: partial correlation: a post facto attempt to create equivalent groups for the 3rd variable and measure remaining correlation, if still present then 3rd variable is discounted. Intraclass correlation: used when scores organized into groups, describes how similar members of the group are to each other: multivariate analysis, multiple regression: 1 criterion variable and >1 predictor variables. Finds multiple variables that predict the same criterion, and also relative strengths. Y = a + b1x + b2x + b3 x + . etc: factor analysis: large number of variables correlated with each other.