A quantitative multi-response set (quantitative MR-set) allows you to group multiple variables representing the same quantitative measure across different items, brands, or categories. Quantitative MR-sets can also be declared directly in a structured DataTile codebook. Quantitative MR-sets are also included in codebook exports, allowing you to preserve and reuse their configuration.
This functionality is available in codebook v.2, which includes the VALUES sheet. Quantitative MR-set declarations are not supported in version 1.
Declaring a Quantitative MR-set
To declare a Quantitative MR-set, add a row to the VARIABLES sheet and enter MQ in the TYPE column. The alternative marker MRQ is also accepted during import. However, exported codebooks always use MQ. The declaration can use the following columns:
|
Column |
Description |
|---|---|
|
|
Set to |
|
|
Name of the Quantitative MR-set |
|
|
Set label and optional language-specific labels |
|
|
Specifies response categories excluded from calculations |
|
|
References the member dictionary when its name differs from the set name |
|
|
Defines the folder containing the set |
|
|
Controls the set's visibility |
Defining member variables
The variables included in the set are declared in the VALUES sheet.
Member declarations can use individual variable names or naming masks to identify multiple variables.
-
For categorical variables, the corresponding response scale must provide the
MIDPOINTvalues used in calculations. -
For numeric variables, the original numeric values are used directly, so no midpoint scores need to be assigned.
Excluding response categories from calculations
The EXP column allows you to exclude specific response codes from the calculation. This is useful for categories such as Don't know, Refused, or other responses that should not contribute to the average.
Excluded responses are removed from both the sum of scores and the valid response count. They are not treated as zero, which would otherwise distort the result.
The following expressions are supported:
|
|
Behavior |
|---|---|
|
Empty |
Includes all response categories |
|
|
Explicitly includes all response categories |
|
|
Excludes categories 98 and 99 |
|
|
Alternative syntax for excluding categories 98 and 99 |
Within parentheses, category codes can be separated by commas or spaces.
Important limitations
Unsupported expressions
Ranges and comparison expressions are not supported in EXP. For example, >=150, 1-3, or 98, 99 without the required exclusion syntax are invalid and will cause the codebook import and database upload to fail.
Codes absent from the scale
If an excluded code is not present in a variable's response scale, it does not cause an error. The database can still be uploaded successfully. This allows the same codebook to be reused across multiple survey waves, even when some response categories are absent from particular waves.
Excluding individual variables matched by a mask
A codebook declaration cannot exclude a specific variable from a naming mask. For example, you cannot declare all variables matching TIME_* while excluding only TIME_INTERNAL within the same mask expression.
Exporting Quantitative MR-sets to a codebook
Quantitative MR-sets created in the Meta Editor are included when exporting a codebook. The exported codebook preserves the set declaration and its configuration, allowing the structure to be reused during subsequent imports.
The exported type marker is always MQ, even if the original declaration used MRQ.
This makes it possible to manage Quantitative MR-sets through either the DataTile interface or a codebook file, without having to recreate the set manually after exporting and importing its metadata.