PSYC 3010 Study Questions and Correct Answers

What are marginal means? Marginal means for one factor are the means for that factor averaged across all levels of the other factor What are cell means? Means for a factor across all levels of the other factor In a graph of a 2-way factorial ANOVA how would you identify the simple effects of each factor? If lines are not horizontal there are simple effects. - You predict that the employees with secure employment will be more productive than those with insecure employment; - and that the difference between secure and insecure employment will be larger for those who are physically healthier (compared to employees who are physically weaker), - especially among those whose supervisors adopt an autonomy- supportive supervision style. Assuming that the 3-way interaction is significant in a between-participants factorial ANOVA, what follow-up tests would you focus on to investigate your hypothesis directly? 1) Simple interaction effects between job security and physical health at each level of supervision style 2) Simple simple effects of job security at each level of physical health, at each level of supervision style. In a standard multiple regression analysis two predictors, X1 and X2 account for 60% of the variability in the criterion. If the semi-partial correlations are .2 and .3 respectively, which of the following is true: a) The squared partial correlation of X1 and the DV is .09 (i.e., .04/.44) b) The squared partial correlation of X2 and the DV is .23 (i.e., .09/.40) c) The squared partial correlation of X2 and the DV is .09 (i.e., .09/.96) d) Both (a) and (b) a) The squared partial correlation of X1 and the DV is .09 (i.e., .04/.44) What is squared partial correlation (pr^2)? The proportion of residual variance in the criterion uniquely accounted for by that predictor What is sr^2 squared semi-partial correlation? The proportion of variance in the criterion uniquely accounted for by that predictor. What does B weights give you a measure of? What change in units of the DV would be expected given a one unit increase in the IV. In a regression analysis the observed variability in the criterion, Y , is partitioned into two components, SSregression and SSresidual. What is SSregression the sum of? Squared deviations of predicted scores (y hat) from the mean of Y [y hat from Y]