4When to Use Nonparametric Tests When the dependent variable is nominalWhat are ordinal, nominal, interval, and ratio scales of measurement?Used when either the dependent or independent variable is ordinalUsed when the sample size is smallUsed when underlying population is not normal
5Limitations of Nonparametric Tests Cannot easily use confidence intervals or effect sizesHave less statistical power than parametric testsNominal and ordinal data provide less informationMore likely to commit type II errorReview: What is type I error? Type II error?
6Chi-Square Test for Goodness-of-Fit Nonparametric test when we have one nominal variableThe six steps of hypothesis testing1. Identify2. State the hypotheses3. Characteristics of the comparison distribution4. Critical values5. Calculate6. Decide
13A more typical Chi-Square Evenly divided expected frequenciesCan you think of examples where you would expect evenly divided expected frequencies in the population?
14Chi-square test for independence Analyzes 2 nominal variablesThe six steps of hypothesis testing1. Identify2. State the hypotheses3. Characteristics of the comparison distribution4. Critical values5. Calculate6. Decide
24Relative RiskWe can quantify the size of an effect with chi square through relative risk, also called relative likelihood.By making a ratio of two conditional proportions, we can say, for example, that one group is three times as likely to show some outcome or, conversely, that the other group is one-third as likely to show that outcome.
25Adjusted Standardized Residuals The difference between the observed frequency and the expected frequency for a cell in a chi-square research design, divided by the standard error; also called adjusted residual.