Threshold

The Row and Column threshold feature in mTAB provides the ability to select a range of data in a single row or column, and remove rows or columns which fall below a specified threshold value.

To Create A Threshold Request

1. If you wish to delete rows which fall below a certain threshold value, move the cursor to the key column you want to use to determine you threshold request and highlight at least 2 or more rows. At this point, mTAB will automatically know that you want to perform a row threshold. mTAB also knows to include every response in the row question, so it's not necessary to highlight every response row in a question, unless you wish to perform this action on several row questions.

If you wish to delete columns which fall below a certain threshold value, move the cursor to the key row you want to use to determine you threshold request and highlight at least 2 or more columns. At this point, mTAB will automatically know that you want to perform a columns threshold. mTAB also knows to include every response in the column question, so it's not necessary to highlight every response column in a question, unless you wish to perform this action on several column questions.

2. Once you have highlight the appropriate range, choose from one of the following:
   • From the Data menu, choose Threshold.

   • Press CTRL+T.

mTAB will display the Row Threshold or Column Threshold dialog box.

3. If there is more than one data type for the range of data selected, you must choose a key data type to which the threshold will be implemented. So if you wish to remove row responses which fall below 10.00%, you might want to choose a percentage data type such as % Column Subset or % Column Sample.

4. Type in an appropriate threshold value. So in the example in step 3, you would want to type in 10.00 (there is no need for the % sign).

5. If you are performing a Column Threshold, and also have a third level question or study selected, you will also need to choose which third level column you wish to use.

6. Choose OK to continue.

7. Depending upon type of data formats currently chosen, you may have to rerun the tab. This is true for any type of subset %.
   

See Also:

• Data Command Options