Use non-parametric tests with nominal or rank data, skewed data, or if the groups show unequal variance. The chi-square test for independent samples is obtained from the Analyze /Descriptive Statistics /Crosstabs procedure, not from Non-parametric Tests. Rank correlation is obtained from Analyze /Correlation. All other non-parametric tests are obtained from Analyze /Nonparametric Tests. Non-parametric tests are used when the data does not lend itself to parametric statistical analysis because it is nominal or rank data, or is skewed, or the groups show unequal variance. In this chapter only the more commonly used ones are considered, but others will be found in the same menu as those described here. It is important to distinguish between dealing with nominal (frequency) data and dealing with ordinal data. If you have counted the number of cases or people who appear in certain categories, the data is nominal and the chi-square test, the binomial test ...

Users without a subscription are not able to see the full content on this page. Please, subscribe or login to access all Methods content.

Click here to see full text

Articles in Google Scholar by