News for hackers. Stuff that matters.

A comment on A/B test improved your website's conversion rate? Not so fast.

Re:A/B test improved your website's conversion rate? Not so ... by clircle on Friday January 07, 2022 @02:05PM (#29843293)
It seems statistically dubious to me that the point k = infinity is in the sample space and that the model is well defined.

Does this model require a proper prior on p?

Cool blog post.

[ Parent | on HN ]
Re:A/B test improved your website's conversion rate? Not so ... by volkale on Sunday January 09, 2022 @03:43PM (#29867139)
- Using the point k=infinity is how I would define it mathematically. In the Stan code I mapped that point to k=-1.

- I don't think a proper prior is required.

- Thank you :)

(Disclaimer: I am the author of the blog post.)

[ Parent | on HN ]
Re:A/B test improved your website's conversion rate? Not so ... by clircle on Monday January 17, 2022 @05:00PM (#29972169)
On more reflection... the support of p is finite, so the prior ought to be proper.
[ Parent | on HN ]