I have Tableau reports where I was able to implement significance testing on percentages using resources from Steve Wexler and a few others but I don't see a lot of resources on how this can be done on means. Basically, I show a month-to-month comparison of the average satisfaction (0 to 10 scale) and I want to show if there is a significant difference from the previous month. Can anyone show me how this can be implemented?
Hi @Roderick Arcega ! I've been looking for the same thing - reflecting MOE for a mean -- and I got it figured out.
My statistician nephew Roy McKenzie provided the calculation needed:
mean (+/-) [1.96 x (the sample standard deviation) / square root (number of respondents)]
I got it built and working in Tableau. Many thanks to @Steve Wexler (Member) for teaching me how to build my survey visualizations properly and providing the solution for CATA items. I'm happy to contribute by figuring out how to do this with means (for rating questions etc.).
I've attached a workbook. You'll see a viz of average ratings (you can change the view using the pulldown to see the average rating of all respondents or to view them by defined segment).
The Details sheet shows you the fields needed for the calculation. In the MEAN MOE chart, you can see the final result in the Tooltips.
My data isn't a time series, so I'm sure you'll need to modify some things for your particular situation -- and maybe Steve's post will provide some guidance there -- but I hope this helps! Let me know if you have any questions!
