please ignore everything i have said or done in the past
seen from United States

seen from Malaysia
seen from China

seen from United States
seen from United States
seen from United States
seen from United States
seen from United States

seen from United States
seen from Malaysia
seen from China
seen from United States
seen from France
seen from United States
seen from United States
seen from United States

seen from Germany
seen from Malta

seen from Canada

seen from United States
please ignore everything i have said or done in the past
The sample-ratio-mismatch in AB testing.
Source: https://www.linkedin.com/posts/ronnyk_experimentguide-abtests-activity-6954129174039068672-pLwN
Looking at segments in A/B tests, or controlled experiments, is very useful, but there are dangerous pitfalls. It is possible to improve c
Reply-Reply to Purified-Zone: A/B See?
purified-zone replied to your post “eightyonekilograms: Inspired by a recent post, which the user asked...”
wtf is ab damn wikipedia aint helpin shit
It’s split-testing. Here’s The Wikipage. Wiki can tend towards the jargonistic, so to explain: it’s just taking two slightly different versions of Something, and showing them to an audience sample to see which one is liked better by your audience. Like op says: this is great for telling you which is liked better but, unless you take steps to counter it, it doesnt tell you anything about the Amplitude of the like/dislike.
We Use a Simple Example to Explore the Ins and Outs of A/B Testing (a.k.a. Hypothesis Testing)
HT @DataSciNews #datascience
to the tune of Hallelujah by Leonard Cohen: somebody once told me the world is gonna roll me, i ain't the sharpest tool in the shed
talking to my therapist: please ignore everything i have said in the past
https://twitter.com/gershbrain/status/1250467765632348162?s=21
Good reads on A/B testing
The math behind A/B testing: https://web.archive.org/web/20150921174256/https:/developer.amazon.com/public/apis/manage/ab-testing/doc/math-behind-ab-testing
Data science you need to know: A/B testing. https://michael-bar.github.io/Introduction-to-statistics/AMP-2-RCT-principles.html
5 things to know about A/B testing: https://www.kdnuggets.com/2018/09/5-things-know-about-ab-testing.html
Optimizely’s introduction on A/B testing: https://www.optimizely.com/optimization-glossary/ab-testing/
How now to run A/B tests: https://www.evanmiller.org/how-not-to-run-an-ab-test.html
Guidelines for A/B testing: https://hookedondata.org/guidelines-for-ab-testing/