Confidence intervals: Digital Event December 2015

What could be more straightforward than the confidence interval? You compute the mean shoe size of a random sample of first-graders and surround it by whiskers that are roughly twice the standard error of that mean. Presumably you can now have 95% confidence that the “true” value of first-graders’ shoe size, in the population at large, is within the interval defined by the whiskers?

Actually, no. Confidence intervals can be deceptive, and the posts in this digital event take up the various ways in which confidence intervals can be misleading: