I have a user journey where I have data of the format:

userID, did_interact_with_feature(0/1), did_convert(0/1)

I want to verify the hypothesis that if a user is engaging with the feature, he's more likely to get converted.

Now I can get the % of user who engaged in feature and then got converted. But I seem to have hit a mental block here.

I was leaning toward a z-test, but could not formulate the problem.

Any help really appreciated.


Okay, thanks to this post, I was able to test this. The test we need is a Chi-square test for approx results and Fischer Test for exact variables.

Given, the variables I had were categoric (engaged:yes/no and converted:yes no) in nature, the base assumption was true.

Now, First I created contingency table for each of those engaged and converted with reference from here.

There after, calculated the expected value for each of the cells in table. Injected the formula and voila, I had the chi-square vale. Further compared with chi-square value table to get the p-value.

This resulted in testing whether the variables are independent or not.

This is what the end results look like: enter image description here

Reference: https://www.socscistatistics.com/tests/chisquare2/Default2.aspx

| improve this answer | |

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.