PSYCH 2300 Chapter Notes - Chapter 9: Longitudinal Study, Regression Testing, Covariance
21 Feb 2018
School
Department
Course
Professor
Document Summary
Psych 2300 - chapter 9: multivariate correlational research. Longitudinal designs, multi-regression designs, and the pattern and parsimony approach are all multivariate designs , involving more than 2 measured variables. These techniques are helpful for establishing causality when experiments are hard/impossible to run. A longitudinal design can provide evidence for temporal precedence by measuring the same variables in the same ppl at several points in time. Cross-sectional correlations test to see whether 2 variables, measured at the same point in time, are correlated. Autocorrelations determine the correlation of 1 variable w/ itself, measured on 2 diff occasions. Researchers are most interested in cross-lag correlations which show whether the earlier measure of 1 variable is associated w/ the later measure of the other variable. Addresses the directionality problem and helps establish temporal precedence. Helps investigate how ppl change over time (in longitudinal studies) A study might show that both correlations are significant. Correlation 1 is significant, but not 2.
