I find it helpful to keep in mind that the traditional statistical significance test is a statement about a conditional probability. i.e. it's the probability of the data given the hypothesis (the null hypothesis). But what many actually want is the probability of the hypothesis given the data. Sometimes these are referred to as the frequentist vs. bayesian approach. There's a helpful recent podcast here by with author of Trustworthy Online Controlled Experiments https://music.youtube.com/podcast/hEzpiDuYFoE