Abstract
This article describes a computer-assisted classroom demonstration illustrating the consequences of excluding significant findings from interpreting published literature. This demonstration, based on tenets of the Central Limit Theorem, stimulates research interpretation when the full range of results are available compared with the subsample of significant results only. Results demonstrated that (a) exclusion of nonsignificant findings positively biases research interpretation and (b) smaller sample sites are prone to greater bias when significant results are excluded from research interpretation.