Answers are grounded in this paper and cite their sources.
When separate 100(1-α) percent confidence intervals on two population means overlap, the means may or may not be significantly different at the 100α percent level. This phenomenon is explored analytically and numerical examples are given.
No takes yet. Share an insight, caveat, or question.
Donald R. Barr (1969) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: