Crosstab reports show the relationship between two or more survey questions. It provides a side-by-side comparison of how different groups of respondents answer the questions.
While an overall survey results view provides a summary of the data, crosstabs are helpful when you want to compare the differences and similarities between different groups of respondents. For example, with crosstabs, you can compare how males responded versus females.
When creating a crosstab, the question you believe changes or affects the response to the other question should be the banner/column question. The stub/row question should then be the question that would be affected by the banner.
In the above example, the banner is Income and the stub is “How often do you usually purchase beauty products?” In this crosstab, you can see if income affects beauty product purchase frequency.
When viewing a crosstab report, you’ll notice shaded areas called hot spots. These represent where there is more overlap between banners and stubs. It’s used to visually indicate where there may be data of interest. Areas with the most overlap will be shaded darker.
The crosstab view also includes the following:
- Chi-Square: This compares two variables in a contingency table to see if they are related. A low value for chi-square means there is a high correlation between the two sets of data.
- Degrees of Freedom: This is the number of values in the final calculation of a statistic that are free to vary.
- P-value: This is used in hypothesis testing to help support or reject a null hypothesis. The smaller the p-value, the more important or significant are the results.