e-Articles (Chapter 9)
Here are the titles of some full-length research articles that illustrate concepts discussed in this chapter. To view any article on-line, simply click on its title.
Shows how the hypothesis testing procedure can be used to see if a correlation coefficient is significantly different from zero. Such a test was performed 10 times, with results presented in Table 5.
Illustrates the use of the hybrid approach to evaluating correlational null hypotheses. For one r in Table 1, p < .001; for three, p < .01,; and for one, p < .05.
In this study, each of several bivariate correlations was tested for significance. Some of these correlations were computed using Pearson's technique; others were computed using the point-biserial technique. See (1) the short section entitled "Data Analysis" and (2) Tables 3 and 4 and the authors' discussion of these tables.
Illustrates how the the square of a correlation coefficient can, at times, suggest that a statistically significant r is not significant in any practical sense. (See the final paragraph prior to the "Summary.")
Copyright © 2012
Schuyler W. Huck