Table : TABLE E.2 Category 2 Statistics When there are one or more nominal independent variables and a scale dependent variable, examine the data to see which test is appropriate to use. Begin by determining the number of independent variables. If there is just one independent variable, use the accompanying chart. (When there are two or more independent variables, we use a form of ANOVA; see Table 14-1.) The first two columns in the chart identify the number of levels of the independent variable and the number of samples. For two levels but one sample, choose either the z test and single-sample t test, depending on whether you know the population standard deviation; for two levels and two samples, choose either the paired-samples t test or the independent-samples t test, depending on the research design. For three or more levels (and the matching number of samples), choose either a one-way within-groups ANOVA or a one-way between-groups ANOVA, a decision that is also dependent on the research design.

Number of Levels of Independent Variable	Number of Samples	Information About Population	Research Design	Hypothesis Test
Two	One (compared with the population)	Mean and standard deviation	—	z test
Two	One (compared with the population)	Mean only	—	Single-sample t test
Two	Two	—	Within-groups	Paired-samples t test
Two	Two	—	Between-groups	Independent-samples t test
Three (or more)	Three (or more)	—	Between-groups	One-way between-groups ANOVA
Three (or more)	Three (or more)	—	Within-groups	One-way within-groups ANOVA