# Non Parametric Tests

Assume that each of the following studies cannot be analyzed using a parametric procedure. For each of the following studies (below), indicate the appropriate nonparametric procedure, and explain why you chose it. NOTE: Would you use Spearman rank-order correlation coefficient, Mann-Whitney U test, Wilcoxon T test, Kruskal-Wallis H test, or Friedman X2 test.

a. One group of mommies has played classical music for their babies every day for 6 months while another group of mommies has not. The babies were tested at the end of six months, to test for statistical significance, on whether their babies had developed motor coordination skills or not.

b. College freshmen with test anxiety are assigned to three groups. One group receives free individualized counseling, one group participates in a class to teach them how to reduce their anxiety, and the third group receives no treatment. They are tested to determine if there is a significant difference in the anxiety level (high, medium, and low).

c. A survey of local residents has been conducted to determine the level of support for a new shopping plaza. Those surveyed were allowed to respond in one of five categories - strongly support, support, no opinion, do not support, strongly do not support. The residents were surveyed as they entered the new shopping plaza and then the same survey was sent out again to them two weeks later.

Â© BrainMass Inc. brainmass.com March 4, 2021, 10:43 pm ad1c9bdddfhttps://brainmass.com/statistics/mann-whitney-u/non-parametric-tests-356429

#### Solution Preview

First, let's go over when each of those statistical procedures would be used ...

1. Spearman correlation coefficient: this is used when you are interested in the relationship between two variables. It's parametric counterpart is the Pearson correlation coefficient (r).

2. Mann-Whitney U test (also called the Wilcoxon rank-sum test): this is used to compare the values of two independent samples. It is like the Student's t-test.

3. Wilcoxon T test (also called the Wilcoxon signed-rank test): this is used to compare the values of two related samples or repeated measures. It is like the paired Student's ...