UPCOMING WEBINAR: 10 Market Research Predictions Over the Next 4 Years Pairwise inclusion of missing values is the default option for comparing columns in a grid question. This article shows you the different options for column comparisons.
Requirements
- One or more tables structured as follows:
- A SUMMARY table using one of the following types of variables sets: Numeric - Grid, Binary - Grid, Nominal - Multi where the variables are in the columns of the tables.
- A crosstab where the variable set in the Columns is a Binary-Multi.
Method - Pairwise inclusion of missing values
This is the default option. What it means is that when columns are compared, they are compared using only respondents with complete data on all the variables that correspond to the columns. Casewise deletion is employed if an ANOVA-Based Column Comparison has been specified.
Method - Casewise exclusion of missing values
This involves only performing comparisons using respondents with complete data on all the columns being compared. This occurs automatically when using ANOVA-Based Column Comparison. It can be made to occur with any table by application of a filter.
Method - Dependent tests
These tests use all the data that is available for performing the test.
Dependent samples tests are statistical tests explicitly designed for the problem in this example. Two notes of caution about dependent samples tests:
- They are not recognized in the statistical literature. That is, while a number of market research software programs provide these tests, there is no body of published work supporting their validity.
- The tests assume that the data is missing completely at random and, as this assumption is often not appropriate in survey research, these tests should generally not be applied without first checking this assumption. A way to check the assumption is to see if the responses of people with missing data are systematically different to those without. This comparison is outlined in Example 2 of this article: How to Perform Column Comparisons with Missing Repeated Measures Data.
To apply dependent tests:
- Select the table or tables in which you wish to modify the statistical testing assumptions.
- Select Appearance > Significance > Advanced.
- On the Test Type tab, change the Proportions test > Survey Reporter Proportions or, if testing means, Survey Reporter Means.
- On the Column Comparisons tab, change Overlaps > Dependent.
- Click Apply to Selection or Set as Default.