Going fast! #DataquestChallenge Premium Annual Offer:
500 get 50% & the next 1000 get 40% off.

Guides on how to perform a good A/B test

A number of data analyst roles I’m looking at expect candidates to have experience with A/B testing. Not all roles expect this, but if there’s any work you have to do with the Marketing team, it’s basically required.

Does anyone know of some good resources on where I can learn how to do an A/B test? This is obviously easier to do as part of a company with a website that already attracts a lot of traffic. So I’m not sure how I’d approach this as an independent learner.

I came across this course:

I am not an expert but I believe this course could be a good starting point. Let me know if you found it useful or not.

Well A/B Test is just a randomized controlled trial (just rebranded). So, if you are going to want to learn how to run this, you honestly might be better off just going over the ins and outs via Google and then get some access to some data that you can get from certain research papers on PubMed since it’s publically available (albeit really specific). You can either use their original hypothesis or make up another one and then essentially run both a descriptive (i.e., chi-square, T-test, ANOVA) + inferential analysis (i.e., essentially either a linear or logistic regression) to test out your hypothesis.

Thanks, guys. I ended up getting hired by a team that performs rather complex experiments, despite my lack of experience. I’m learning on the job now.