PSYC 3010 Review Questions and Correct Answers

Conditional Y values are normally distributed around the regression line Homoscedasticity: variance of Y values are constant across different values of Ŷ (homogeneity of variance) No linear relationship between Ŷ and errors of prediction Independence of errors assumptions of multiple regression - distribution of residuals Variables are normally distributed Linear relationship between predictors and criterion Predictors are not singular (extremely highly correlated) Measured using a continuous scale (interval or ratio) assumptions of multiple regression - scales (predictor and criterion scores) Occurs when predictors are highly correlated (.80 - 90) Multicollinearity leads to unstable calculation of regression coefficients (b), even though R2 may be significant multicollinearity & singularity Tolerance = (1 - r2x) R2x is the overlap between a particular predictor and all the other predictors Low tolerance = multicollinearity singularity High tolerance = relatively independent predictors tolerance Relationship between a criterion and a predictor varies as a function of a second predictor The second predictor is usually called a moderator Moderator enhances or attenuates the relationship between criterion and predictor interactions in MR Moderation: focus is on the direct X Y relationship: Z changes or adjusts it (often uncorrelated to IV) Mediation: focus on the indirect relationship of X Y via M, X causes Y because X causes M, which in turn causes Y (is correlated with IV) moderation versus mediation 1. Does the XZ interaction contribute significantly To the prediction of Y? Sig Rchange