Question

Consider the scenario where a Type II error is more severe than a Type I error. Pick the most reason- able value for α.

(a) 0.01 (b) 0.05 (c) 0.10 (d) 0.95

Answer 1

Error corresponding to rejecting the null hypothesis when it is true is type I error.

Error corresponding to not rejecting the null hypothesis when alternative hypothesis is true is type II error.

so we can't reduce the both error at the same time. i.e. if we want to minimize the type I error, type II error will increased and if we want to minimize the type II error, type I error will increase.

Normally type I error is more severe than a type II error. But here it is given that Type II error is more severe than a Type I error. so we want to minimize the type II error corresponding to reasonable type I error.

Type I error is measured by alpha.

To minimize the type II error, we should take a risk of high type I error.Therefore the maximum reasonable type I error can be of 10% among the 1%,5%,10% & 95%. because we cannot take 95% which is very high,