Wise Use Of Null Hypothesis Tests: A Practition... [ 90% QUICK ]
It measures the probability of seeing your data if the world is actually boring ( H0cap H sub 0
With a massive sample size, even a tiny, useless difference will be "statistically significant."
Did I check my data for outliers and normality before testing? Is my sample size justified by a power calculation? Am I reporting the effect size alongside the p-value?