76. *Refer to Problem 6.37

a) For what values of the number of wins X can you reject Ho = .50 in favor of H.50. using a = .05?

b) For what values of X can you reject Ho using a = 01? (Note: For small samples with discrete data, it may not be possible to achieve very small P-values.)

c) * Suppose you test Ho using a = .05. What is the probability of making a Type I error? (Note: For discrete distributions, the actual chance of Type I error inay be less than the intended chance. It is better simply to report the P-value. Unfortunately, this fact also adversely affects small-sample confidence intervals for proportions, making them con- servative.)