Optimal power of a hypothesis test

47 Views Asked by At

I am doing a hypothesis test, with h0: p=0.5, with H1:p>0.5. If I want to test different values of p that are greater than 0.5, with a fixed significance level, say 0.05, how does the choice of p effect the validity of my test. From tests I have done I have seen that the choice of a high value of p>0.8 results in a high power (meaning a low chance of type 2 error). Is there any drawback to using this? E.g. would this effect the probability of getting a type 1 error? Andif so is there an optimal power value to have?