OUTLINE FOR CHAPTER 3

1. The Key Concept Behind Correlation: "Relationship"
   1. The need for data on two variables
   2. What's the basic question being addressed in discussions about correlation?
   3. Three possible answers to the basic correlational question:
      1. High-high, low-low
      2. High-low, low-high
      3. Little systematic tendency one way or the other
2. Scatter Diagrams
   1. What they look like
   2. How to interpret one
   3. The notions of "strong," "moderate," and "low" relationships
3. The Correlation Coefficient
   1. How it's symbolized
   2. It's numerical range
   3. How to label different points on and sections of the continuum of possible values
4. The Correlation Matrix
   1. Determining the number of bivariate correlations among k variables
   2. The purpose and general appearance of a scatter diagram
   3. Saving space when showing one correlation matrix (or two correlation matrixes)
5. Different Kinds of Correlational Procedures
   1. Quantitative vs. qualitative variables
   2. Dichotomous, nominal, ordinal, and "raw-score" variables
   3. True and artificial dichotomies
   4. Specific correlational procedures:
      1. For two raw-score variables: Pearson's product-moment correlation
      2. For two sets of ranks: Spearman's rho and Kendall's tau
      3. For one raw-score variable & one dichotomous variable: biserial r & point-biserial r
      4. For two dichotomous variables: phi and tetrachoric r
      5. For two nominal variables: Cramer's V
6. Warnings About Correlation
   1. Correlation and cause-and-effect
   2. The coefficient of determination and explained variability
   3. Outliers and their influence on correlation coefficients
   4. Linear and curvilinear relationships
   5. Correlation and independence
   6. The subjectivity nature of adjectives used to denote relationship strength

7. A Summary of the Abbreviations & Symbols Associated with this Chapter
   

   r

   rs

   r

   rpb

   rbis

   f

   V

   r2

Copyright © 2012

Schuyler W. Huck
All rights reserved.