I am very new to JMP, I should start by saying that. I have a table of thousands of events, within each event there may be multiple units associated with that event. I only want to look at units responding to events in my area, and units of the immediate neighboring areas responding to events within my area. So I want to ignore/hide the rare case that there is a unit that responds from a region far away; such instances only occur 15 times or less for a particular unit from far regions.
What's the easiest way to hide units from far regions that have responded into my area less than 15 times in the table?
You can used the distribution platform to identify which events occur fewer than 15 times and then use the local data filter to hide and exclude them from your analysis.
If you know what areas you are interested in, and it is a moderate number...let's say, 10 or less, a simple way to select all of those records, is to go to the column that represents the "area" you are referring to. Click on one cell for the first area you want included. Then scroll down to a row that has the next area you want included. Hold down the CNTL key and click on the area's column cell for that row. Repeat the selections until all areas you are interested in have one of the rows from those areas selected. Now hover over one of the selected cells with the cursor, and right click and select "Select Matching Cells".
All of the rows for all of the areas that you had selected will now be selected. Now you have a decision on which method of eliminating the unselected rows from the analyses you are going to do.
1. You can set all of the unwanted rows to be Hidden and Excluded. To do this, you need to invert the row selection
a. Move your cursor to the Row State Column(the column that has the row numbers in it), and hover over one of the selected rows.
b. Right click the mouse and select "Invert Selection"
c. Move your cursor over one of the newly selected rows, right click and select, "Hide/Exclude"
2. You could also just create a subset of the data table. So starting after you have selected all of the rows from all of the areas you are interested in:
a. Go to the pull down menus
b. Select Tables==>Subset
c. Make sure that the choices of "Selected Rows" and "All Columns" have been selected
d. Click on OK
You will now have a data table that only has the records you are interested in.
You can also use a Data Filter to do the selections.
1. Go to the pull down menus
2. Row==Data Filter
3. From the data filter window, select the area column
4. Click on Add
Once the filter is created make sure the "Select", "Show" and "Include" options are selected
Now you can just select the areas you are interested in. The areas of non interest will be hidden and excluded