A group of mountain climbers participated in a trial to investigate the usefulness of the drug acetazolamide in preventing altitude sickness. The climbers were randomly assigned to receive either drug or placebo during an ascent of Mt. Rainier. The experiment was sup-posed to be double-blind, but the question arose whether some of the climbers might have received clues (perhaps from the presence or absence of side effects or from a perceived therapeutic effect or lack of it) as to which treatment they were receiving. To investigate this possibility, the climbers were asked (after the trial was over) to guess which treatment they had received. The results can be cast in the following contingency table, for which χ2s = 5.07:

Alternatively the same results can be rearranged in the following contingency table, for which χ2s = 0.01:

Consider the null hypothesis
H0. The blinding was perfect (the climbers received no clues).
Carry out the chi-square test of H0 against the alternative that the climbers did receive clues. Let α = 0.05. (You must decide which contingency table is relevant to this question.)

Transcribed Image Text:

Treatment received Drug Placebo 12 21 Guess Correct 20 Incorrect 11 Treatment received Drug Placebo Guess Drug 20 Placebo 11 21 12