<< Chapter < Page | Chapter >> Page > |
In this set of steps, readers are provided with directions on calculating a statistical procedure in which the independent variable and the dependent variable are categorical variables. As such, the only descriptive statistics that can be obtained are frequencies, percentages, and sums. Because the data on which this chi-square procedure is used are grouped data, skewness and kurtosis values are not appropriate. Readers should ensure that the assumptions described in the steps below are met prior to conducting this nonparametric procedure. For more detailed information about the statistical and conceptual underpinnings of this statistical technique, readers are referred to the Hyperstats Online Statistics Textbook at (External Link) or to the Electronic Statistics Textbook (2011) at (External Link)
Check to make sure that both variables are categorical in nature. That is, the variables must have values that are in a restricted range (e.g., 1 or 2 for gender; 1 – 5 for Strongly Agree through Strongly Disagree; 1 – 5 for ethnicity categories).
Check to verify that you have available per cell at least 5 responses (i.e., divide the sample size by the number of cells [number of categories for the IV times the number of categories for the DV] and have a value of at least 5).
Verify that only one response per participant is present. Once these assumptions have been checked and validated, then the Pearson chi-square procedure can be calculated.
Notification Switch
Would you like to follow the 'Calculating basic statistical procedures in spss: a self-help and practical guide to preparing theses, dissertations, and manuscripts' conversation and receive update notifications?