Demonstrate why scientific procedures are necessary to do accurate descriptive research

Demonstrate why scientific procedures are necessary to do accurate descriptive research. There are at least five examples that illustrate the problems with non-scientific description:
1. Demonstrate the inaccuracy of casual observation by staging a minor disagreement with a stranger and then having students describe the encounter and the stranger or by showing the six minute film, Fidelity of Report, available from Penn State.
2. Discuss people's failure to understand the importance of a representative sample. Discuss the acceptance of write-in polls such as those conducted by "Dear Abby" as well as the popularity of call-in polls. In addition, discuss the fact that people are quite willing to accept their own experience as representative.
3. Demonstrate people's belief in the law of small numbers Give students the following "test" question: "A certain town is served by two hospitals. In the larger hospital, about 45 babies are born each day, and in the smaller hospital about 15 babies are born each day. The exact percentage of baby boys varies from day to day. Sometimes it may be higher than 50%, sometimes lower. In a period of one year, each hospital recorded the days on which more than 60% of the babies were boys. Which hospital do you think recorded more such days? Or, do you think they were about the same?" Students who answer "the larger hospital" or "about the same" fail to appreciate the law of large numbers.
4. Discuss people's willingness to totally ignore baseline data in favor of a single, vivid case study.
5. Discuss the availability heuristic. Set up the discussion by asking questions such as: "Are accidents or strokes more common causes of death?" (strokes are much more common causes of death); "Is it safer to fly or drive?"; and "Is r more likely to occur as the first or third letter of a word?" (it is almost three times more likely to occur as the third letter). Then, emphasize that we tend to think that events that are to recall occur more frequently than events that are more difficult to recall. However, this rule of thumb can lead us astray. Therefore, to get an accurate index, we need scientists to objectively record the frequency of events.
Useful references include

Kahneman, D., Slovic, P., & Tversky, A. (Eds.). (1982). Judgment under uncertainty:

Heuristics and biases. New York: Cambridge University Press.

Nisbett, R. E. & Ross, L. (1980). Human inference: Strategies and short-comings of

social judgment. Englewood Cliffs, NJ: Prentice-Hall.

Paulos, J. A. (1988). Innumeracy: Mathematical illiteracy and its consequences. New York:

Hill and Wang.

Back to Chapter 7 Main Menu