OUTLINE FOR CHAPTER 10

1. Introduction
   1. A needed shift in inferential focus: from correlations to means
   2. Reasons why multiple chapters are needed to consider inferences on means
2. Inferences Concerning a Single Mean
   1. The inferential purpose
   2. Interval Estimation
   3. Tests concerning a null hypothesis
      1. The null hypothesis
      2. The two most popular test procedures: t-tests and z-tests
      3. Degrees of freedom (df )
3. Inferences Concerning Two Means
   1. Independent vs. correlated samples
      1. The basic distinction
      2. Three settings that produce correlated samples
      3. The sample sizes, if different, provide a signal as to the kind of samples
      4. Terminology
   2. The inferential purpose
   3. Setting up and testing a null hypothesis
      1. The general and typical forms of the tested Ho
      2. Three settings that produce correlated samples
      3. The three most popular test procedures: t, z, and F
   4. Interval estimation with two means
4. Multiple Dependent Variables
   1. Results presented within passages of text or in tables
   2. The Bonferroni and pseudo-Bonferroni adjustment techniques
5. Effect Size Assessment and Power Analyses
   1. Do impressive p-levels signify important findings?
   2. Options for checking to see if a statistically significant result has practical significance too
      1. A computed effect size
      2. Omega squared & eta squared
      3. A post hoc power analysis
   3. Performing a power analysis before data are collected
6. Underlying Assumptions
   1. The four main assumptions . . . and the two discussed most by applied researchers
   2. Testing the assumptions (and options if an assumption seems untenable)
   3. Equal sample sizes and the notion of "robustness"
7. Comments
   1. A nonsignificant result doesn¹t mean that the null hypothesis is true
   2. Overlapping distributions
   3. The typical use of t-tests
   4. Practical significance versus statistical significance
   5. Type I and Type II errors

Copyright © 2003 Schuyler W. Huck
All rights reserved.