A multiple response question is one question for which a respondent can give multiple answers.
Multi choice questions need to be dichotomous, and their answer alternatives cannot overlap. If your question has the same answer alternatives, it would create an answer block with duplicate answers. In case your data file has a value of -1 it’s possible to import it as an answer in the regular Import. ID -1. The option to include -1 is available only in detailed import while in quick import the -1 will be excluded from the base if file imported this way.
- A multiple response question is normally in excel or spss stored as one variable per answer alternative. During the import process, Dapresy can merge them together in one variable with multiple answers using a multi choice separator.
- The name for each variable should be on the form: [Question ID] & [Separator] & [Answer ID]. For example Q1_1, Q1_2 … Q1_99.
- The separator should be one valid spss character (for example #, @, _, $), but the character that is chosen as a separator for multiple choice questions cannot be used in the name of any other question type, i.e. in the example above “_” is used as separator. This means that “_” cannot be used in the name for a single choice question etc.
Uploading multiples WITHOUT the options in the MDT (see image below).
This will only be possible with Numeric questions.
In this case is necessary to define the answer alternative text and ID using the "Label" property of each numeric variable. Dapresy is using a fixed separator "-" for answer value/id and answer text distinction (it's not related to multichoice separator). SPSS property "Name" is used only for grouping.
- The system will use the label for the first variable that belongs to the multi response question as question text.
- The value label list can just contain of one answer alternative. This alternative should have the code 1. All other codes and values will be treated as “Not chosen”. For example if the answer for Q1_1 is “Car brand A” the respondents that have answered “Car brand A” should have the code 1 in the data and the value label list should contain 1 with the label “Car brand A”.
To get the base correct there should be variables for those respondents who haven’t received the question and for those who haven’t answered the question etc.
An example of this could be: Name: Q1_99; Label: Which car brands do you know of?
Value label: 1 “No answer”
Another option is to Compute this additional answer option by selecting this on the import screen.