Improvement Insights Blog
p value’s Dirty Little Secret
The American Statistical Association (ASA) has issued a statement about statistical significance and p values. It quotes ScienceNews article from 2010: “It’s science’s dirtiest secret: The ‘scientific
method’ of testing hypotheses by statistical analysis stands on a flimsy foundation.”
Six Sigma spends a lot of time on hypothesis testing using p values, but our use of p values may lack the rigor required. The ASA states: By itself, a p-value does not provide a good measure of evidence regarding a model or hypothesis.