For some analyses, you may only want to see results based on people who had a definitive answer to a question. You can remove these "Don't Know" responses from a variable set and remove those respondents from the sample. This article describes how to go from a categorical table containing a Don't know category:
To a table in which the Don't know category is removed from the table and the remaining responses are rebased to the new total.
- One or more categorial variables containing a Don't Know category or similar response as listed in the technical documentation.
1. You can select one or more tables/variables or an entire data set in your document. Any Don't Know categories within the selected object will be removed.
2. From the toolbar menu, select Anything > Data > Variables > Modify > Remove Categories > Remove Don't Know Categories.
3. If you've selected more than one variable (for example, a page with multiple tables or an entire data set), a notification will be displayed showing which variables were modified, which were the wrong type (not categorical) and which do not contain a Don't Know option/category. Click OK.
- To restore a Don't Know category, select the variable from the Data Sets tree and then from the object inspector on the right, click the Missing values button and change the Don't Know category to Missing Values > Include in analyses, see Value Attributes in Variable Sets for more info on these settings.
- If you would like to show Don't Know categories in your table, but exclude them from mathematical statistics like (sums, averages, etc), see How to Exclude Don't Knows from Averages but Include in Percentages.
How to Rebase Multiple Response Data in Variable(s) to NET
How to Add Top K Category Variables
How to Add Bottom K Category Variables
How to Recode High Values (Capping) in Numeric Variables
How to Recode Low Values (Capping) in Numeric Variables
How to Combine Categories with Small Percentages
Article is closed for comments.