Type the two R calls and their key output lines for the one-proportion test of 60 errors in 500 against p = 0.1, first with the default continuity correction and then without.
Type the two R calls and their key output lines for the one-proportion test of 60 errors in 500 against p = 0.1, first with the default continuity correction and then without.
Answer
> prop.test(60, 500, p = 0.1, alternative = "greater") X-squared = 2.0056, df = 1, p-value = 0.07836 > prop.test(60, 500, p = 0.1, alternative = "greater", correct = FALSE) X-squared = 2.2222, df = 1, p-value = 0.06802
X-squared is z². The default applies a continuity correction, so 2.0056 and p = 0.0784 differ from the hand z = 1.49 (z² = 2.22) and p = 0.0681; correct = FALSE recovers them: √2.2222 = 1.49, p = 0.0680.
R documentation for prop.test (the correct argument); R output from a live Rscript session; original scenarios