Meta-analysis studies using results from observational studies are used in decision making. There is a need to evaluate the reliability of these studies. We use a JMP Add-In to evaluate these studies for p-hacking, trying this and that analysis to get a p-value less than 0.05. We show that p-hacking is a massive problem and that many meta-analysis studies are unreliable.
How to show if a science claim is wrong.
