e-Articles (Chapter 10)
Here are some full-length research articles that illustrate the use of statistical tests on one or two sample means. To view any article, simply click on its title. (NOTE: No claim is made that these articles are perfect in all respects. By carefully reviewing them, you will hone your skills at being able both to decipher and to critique statistically-based research reports.)
Illustrates the use of a set of matched t-tests to compare 2 samples in terms of mean pretest scores on several demographic and weight variables. Each of these tests was conducted in a 2-tailed manner with alpha = .05. See rows 1, 3, 4, and 5 in the report's only table to see the results of these t-tests.
In this study, an unpaired t-test was used to compare the test performance of 2 groups of medical students taught differently over a block of material. The main results of this comparison are presented in Table 2.
In this study, the researchers used an independent-samples t-test to compare the means of 2 groups. In addition, a one-way ANOVA was used to compare the 2 groups. For the t-test results, see the 1st 3 paragraphs of the "Results" section dealing with "Quiz assessment of domain knowledge." For the ANOVA results, see the 2nd, 3rd, and 4th sentences in the 2nd paragraph of the "Sample characteristics" portion of the "Results" section, as well as the final paragraph of "Results."
Illustrates the construction of confidence intervals around Cohen's d index of effect size for t-test comparisons of 2 means. See the portions of the "Results" section called "Overall Knowledge Assessment," "WMD Recognition," "WMD Response, and "Follow-up Test."
Before using t-tests as the main statistical tool in this study, the researchers conducted an a priori power analysis to determine how large their samples needed to be. The researchers' discussion of this aspect of their investigation is worth reading, as it contains the terms "effect size," "Type I error," "Type II error," "power," "alpha," "beta," and "clinically meaningful differences." See the "Data Analysis" and "Sample Size" portions of the article's "Methods" section.
Copyright © 2012
Schuyler W. Huck