Show stats on pivot table | XM Community
Skip to main content
I have a pivot table that shows how boys compared to girls on a self-rating scale of 0-10. Stats-IQ shows me that several of the differences between the two groups are statistically significant. I'd like to be able to show the p-values in the same table so that the degree of significance is a little clearer and allow the readers to see and judge for themselves about the level of significance. But I can't seem to find a way to show the statistics in the same table. They're obviously available, since Qualtrics based it's decision on whether to mark it significant or not would have been based on running those stats. It would also be nice to be able to change or at least report which test was run.



here's a screenshot of the table:

!



Is there a way to show the p-values alongside the other data in this table?
p values cant be shown in seperate columns while arrowas can be taken as reference to determine p-values.

p-value <= .05: one arrow



p-value <= .01: two arrows



p-value <= .001: three arrows
@bansalpeeyush29, thanks for the answer to this. I was assuming those same references for the arrows, so that's a good thing. You stated that the p-values can be shown in separate columns, which is exactly what I'm looking for. Can you please explain how to accomplish this?
So, I just realized that @bansalpeeyush29 said p-values "can't" not "can" be shown. There's really no good programmatic reason these couldn't be shown, since they have to have already been computed in order to indicate significance. What's the chance there's a Qualtrics engineer who could make this happen?
p values cant be added, i suppose the calculation happens at back-end but you can contact support team if there is anyway we can bring these values in our table.
Exactly! I'd love to have this feature enabled. Are any Qualtrics engineers following this conversation?
Hi, @Peter! If you have not yet already, I’d recommend posting this in our Product Ideas category, as it is a feature not already developed by our team. Be sure to review the How to Write a Good Product Idea template and our Ideation Guidelines before you post your idea!
@Kendra,

Thanks. BTW, the way you responded actually prevented this from being attended to. First, you provided an answer that wasn't really the answer at all, but a recommendation on how to get an answer (hopefully). Second, you accepted it immediately, which made it float to the top and was reported in the system as an accepted answer. Because of that, your department head believed that the issue was actually resolved (I know a guy on the inside who let me know this is what happened 😉. In the future, I would recommend that, unless your response actually solves the problem, you not mark the question as answered. Thanks!
Hi @Peter! It looks there may have been some miscommunication here, I apologize! It sounds like you did want to reach out to our engineering team at some point and file a feature request with them. In order to get this request in front of the team (they do not follow this thread), you would need to post this in our Product Ideas category.



However, we did find something that may help you do something very similar to your original request! We'd suggest that you use the Relate function, which would run one overall test differentiating boys from girls, and would yield an explicit p-value. If you have any additional questions about the functionality of our Relate feature, feel free to reach out to our Support team and they'd be happy to assist! 😀

Leave a Reply


Terms & Conditions