I ***do*** wish people wouldn't say ``confidence level'' when they mean ``significance level''. Confidence level refers to estimation and significance level to hypothesis testing. The two are closely related but do not pack the same freight. Moreover, if one indeed wishes to conflate the two ideas, the confidence level of an estimation procedure is ***one minus*** the significance level of the corresponding hypothesis test. cheers, Rolf Turner rolf at math.unb.ca
confidence level of kpss test
1 message · Rolf Turner