Answer each question with at least 100 words and a reference.
1. Many of you have heard of the normal curve (aka “bell-shaped curve”), which according to Cohen, et al. (2013) “is a bell-shaped, smooth, mathematically defined curve that is highest at its center. From the center it tapers on both sides approaching the X -axis asymptotically (meaning that it approaches, but never touches, the axis). … The curve is perfectly symmetrical, with no skewness.” However, in reality, we also may know that data sets may be skewed.
Thus given, and as asked by Cohen, et al. (2013) on page 98, “Why is the normal curve important in understanding the characteristics of psychological tests?”
2. We may agree that the reliability of a test is important. We desire to rely upon the results, e.g. test scores, that may yield from test taking. According to Cohen, et al. (2013), there are several ways to estimate the reliability of a test, e.g. test-retest reliability estimates, alternate-forms or parallel-forms reliability estimates, split-half reliability estimates, et cetera. However, and seemingly appropriately, Cohen, et al. (2013) also advised that “reliability is not an all-or-none matter. A test may be reliable in one context and unreliable in another. There are different types and degrees of reliability” (p. 145).
What are your thoughts on the various methods available to estimate reliability, and which method might you feel more comfortable using, and why?
3. At first glance, test bias and test fairness may appear as polar opposite concepts. However, Cohen, et al. (2013) wrote, “although questions of test bias can sometimes be answered with mathematical precision and finality, questions of fairness can be grappled with endlessly by well-meaning people who hold opposing points of view” (p. 206). Perhaps in relation to this point, Balkin, et al. (2014) wrote, “assessments may be thought to be unfair and in favor of the middle-class Caucasians, who may often have access to resources that may bolster improved performance” (p. 44).
Although the assertions of Balkin, et al. (2014) may seem too simplistic and inconclusive, what are your thoughts on considering it in discussing the differences and similarities of test bias and test fairness?