jamovi

New user here.

I have developed a possibly tortured way of identifying outliers across multiple variables (through transformed and computed variables), and now want to filter my dataset to exclude outlier cases. Outliers are those who have a score of less than 10 in my outlier variable.

My Googling suggests this should be easy to implement, however I'm seeing this error: "Filters may not reference columns using 'V' or column functions" (this appears in read just below my function text box). My row filter formula is = Outliers == 10. Outliers all have a value of 8 or 9.

Help appreciated!

appears in *red

yeah, so hopefully you can see that filters referencing V functions is a problem. the problem is one of an 'infinite loop'.

the filter changes the variable, the variable changes the filter, and the filter changes the variable ... and on it goes.

we do have a solution to this problem planned, but it hasn't been developed yet.

in the mean time there's a few (hackish) ways to solve this. one is to apply the filter, save the results as a .csv, and then reopen that .csv. that excludes all the filtered rows.

alternatively, you can transform the variables you intend to analyse with rules like:

if Outlier == 10 use NA
else use $SOURCE

https://blog.jamovi.org/2018/10/23/tran ... ables.html

none of these are ideal i appreciate ...

jonathon

Thanks so much for your quick reply. I think I understand. I've created a new outlier variable with just raw numbers (not referencing any other var) and it works.

I've run into the same problem and my (also hackish but quick) workaround is: create a new column, then copy-paste the values from the computed column into the new one, and apply the filter to the copy.