•Steps for hypothesis testing
•What does the alpha level signify? What is the critical region? What happens to the
critical region if alpha increases/decreases? What effect does changing alpha have on
your hypothesis test decision?
•Null and alternative hypotheses – what they are, how to construct them for all tests we’ve
covered, and how they differ for one- vs two-tailed tests
•How to find the critical values for z, t (one- and two-tailed) and F.
•Type I vs Type II errors
•Relationship of Type I errors and alpha levels
•What does changing sample size (assuming everything else is held constant) do to: 1)
error terms; 2) critical values; 3) test statistics; 4) effect size
•What does an increase/decrease in variance (assuming everything else is held constant)
do to: 1) error terms; 2) critical values; 3) test statistics; 4) effect size
•What does a larger/smaller difference in means (assuming everything else is held
constant) do to: 1) error terms; 2) critical values; 3) test statistics; 4) effect size
•Differences between directional and non-directional t-tests (hypotheses, critical values)
•Cohen’s d, r2, and confidence intervals for all t-tests
•η2 for ANOVAs
•How to identify a small, medium, or large effect size
•Identifying when a z-test, one-sample t-test, two-sample t-test, or ANOVA is best
•Independent measures design vs repeated/related samples design
•What is a matched-sample design? What kind of test(s) would we use?
•How to write a conclusive summary, including the proper way to report the test statistics.
•Notation. If I show you something like sp2, s(M1-M2), or SSBS, can you tell what test it’s
from?
•What is a difference score?
•How to construct an ANOV A table
•How to perform post-hoc tests using Tukey’s HSD (know how to use the q table)
•Vocab: Independent variables, dependent variables, factors, and levels
•Why don’t we run multiple t-tests when we have multiple groups instead of an ANOVA?
•Systematic vs unsystematic variance
•Between-treatments variance vs within-treatments variance
•The role of individual differences in independent vs repeated measures