STUDY GUIDE: Exam 2

1. Understand what makes attest for independent means different from an analysis in a One-Way ANOVA, in terms of how many "treatment conditions" there are to compare (remember "treatment conditions" has other names like "groups", "levels" and so forth).
2. Understand the main concept of all the following formulas covered in class...t-Tests, ANOVAs and Correlations... in terms of knowing what the "top of the formula's fraction measures" versus what the "bottom of the formula's fraction measures", and what values of each are preferred (like "larger numbers" or "smaller numbers") as well as what it would suggest if the top value and bottom value are "similar".
3. Understand what kind of values we could obtain in a t-test (i.e., "t-stat") and ANOVA (Fratio) that would indicate significance, as well as what the "mean" is for the null hypothesis in each.
4. Know how to calculate anFratio for ANOVAs with a between-groups population variance estimate (MSBetween) and within-groups estimate (MSWithin). You do not need to hand calculate the entire ANOVA, just know what to do with the value given in a scenario for an MSBetweenand an MSWithinto give you yourFratio.
5. Understand when a "post-hoc" analysis is needed (just based on the analyses we have learned in this course so far) and what it tells us (in other words, why we need it as well we how it helps us understand results of the statistics we use it for).
6. Understand what anR2tells us and what is considered a large, moderate, and small value (according to Cohen). It will help to compare it to what we learned about Cohen'sdvalues (which are different values) and to also know the "general idea" of both (i.e., the characteristics of the "desired values").
7. Understand the main difference between a One-Way ANOVA and Factorial ANOVA (meaning how many independent variables they can have in the analysis) as well as why we would choose the more "complicated" one.
8. Know how to report the statistical values in a research report for One-Way ANOVA and Factorial ANOVA (similar to what we learned aboutt-Tests) and be able to distinguish what each element of that writeup indicates. For example, if our writeup ist(20) = 2.45,p< .05, for a t-Test that we calculated, thetis the test we ran, the 20 is our degrees of freedom (df), the 2.45 is our obtainedtstatistic, and thep< .05 is our significance level that lets us know if our results were significant.
9. Understand how to determine the number of "treatment conditions" (also called groups or levels) and "number of participants" there are in a study based on the reported statistics. For this one, the basic idea is to understand the values reported in ANOVA statistics in terms of the degrees of freedom that are listed in the writeup (in the parentheses) and knowing how if your study had "independent groups" or "repeated measures".
10. Understand what kind of "Factorial design" you have based on scenarios given. This will be like when we looked at "type of study" and "amount of sleep" in which "type of study" had 2 levels (massed and spaced) and "amount of sleep" had 3 levels (2 hours, 4 hours, and 6 hours) and that resulted in Factorial design called a "2x3".
11. Understand the difference between Factorial ANOVA names like "two way" and "three way" and what the "two" and the "three" indicate.
12. Understand the difference between the terms "main effect" and "interaction" and how to determine the number of each we can expect to look for in a study based on a scenario given. In the exam you can be asked to establish how many "main effects" or "interactions (i.e., interaction effects)" or "total effects" there are in a scenario.

1

1. Understand how to read Factorial designs when they are in a "chart" as well as a "graph" and how to establish if there are main effects and/or interactions present by looking at "marginal means" and "cell means". Example of a chart (left) and graph (right) are below...
2. Know how manyFratios are figured in a Factorial ANOVA (e.g., for a two-way versus a three-way ANOVA).