e-Articles (Chapter 5)
Here are some full-length research articles that illustrate sampling procedures and problems. 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.)
In describing their online survey, the researchers openly discuss several possible methodological problems that can taint a study's results: a possible mismatch between the obtained sample and the target population (referred to in this article as a "coverage error"), sampling the wrong people (referred to as a "sampling error"), nonreponse bias, and poorly designed surveys. See the sections entitled "Methodological Issues," "Validity and Reliability," "Data Selection," and "Results." Also, take a look at Figure 3.
This study involves a two-fold kind of response rate problem. In an earlier study, 791 students agreed to participate out of 1,384 who were invited. Then, for the current study, only 438 of the 791 students participated. The researchers noted this problem when citing the study's limitations in the "Discussion" section.
The sampling procedures used in this study were extremely refined, as indicated in the portion of the "Methods" section called "Sampling scheme." Despite the researchers' efforts to collect data from a random sample, the participation rate was a disappointing 64.1%, as indicated in the 1st paragraph of the "Results" section.
Illustrates the use of a 10% stratified random sample. Not to be overlooked is the extremely high response rate. See the "Data collection" portion of Section 1.
Illustrates the use of (and problems associated with) a snowball sample. See the 5th sentence of the abstract, the "Participants" portion of the article's "Methods" section, and the portion of the "Limitations and Future Research" section called "Sampling and Sample."
Copyright © 2012
Schuyler W. Huck