| I added the pdf of free chapter of 'Trustworthy Online Experiments' and then had this strange exchange... way too agreeable. Me: Bukowski said: "If you're going to try, go all the way". How would you do this with an AB test? PDF: While Charles Bukowski's quote is not directly related to A/B testing, you can apply the spirit of his words to your approach to A/B testing. To "go all the way" with an A/B test, you should aim to test as many variables as possible in order to get the most accurate and comprehensive results. This means testing multiple variants, adjusting multiple parameters, and collecting data from a large sample size over a significant period of time. By doing so, you can ensure that your results are reliable and that you have a clear understanding of which variant performs better. (Page 21) Me: But if you go all the way (in the way you described), wouldn't you be walking in a garden of forking paths? PDF: You raise a valid concern. When conducting an A/B test with many variables and parameters, there is a risk of encountering the "garden of forking paths" problem. This refers to the issue of having many possible paths to take when analyzing the data, which can lead to false positives or overfitting. To avoid this problem, it's important to have a clear hypothesis and plan in place before conducting the test, and to limit the number of variables being tested at once. Additionally, you should use appropriate statistical methods to analyze the data and correct for multiple comparisons. By taking these precautions, you can minimize the risk of encountering the garden of forking paths problem and ensure that your results are reliable. (Page 21) Me: So what's a better way to go all the way? PDF: A better way to "go all the way" with an A/B test is to focus on testing a few key variables that are most likely to have a significant impact on your metrics. This approach is sometimes called "full factorial testing" or "multivariate testing". By testing a smaller number of variables, you can reduce the risk of encountering the garden of forking paths problem and increase the statistical power of your test. Additionally, you should use appropriate statistical methods to analyze the data and correct for multiple comparisons. By taking these precautions, you can ensure that your results are reliable and that you have a clear understanding of which variables have the biggest impact on your metrics. (Page 21) |