QA6 - Hypothesis Testing Flashcards
Explain the difference between Type I and Type II errors and how these relate to the size and power of a test
Type I is rejecting a true null hypothesis, probability is the size and denoted alpha
Type II error is not rejecting null hypothesis when alternative is true, denoted (1 - beta) and is the power of a test
Understand how a hypothesis test and a confidence interval are related
Confidence interval will contain the null hypothesis if not rejected
Explain what the p-value of a hypothesis test
Probability of observing a test statistic more extreme than computed when the null is true
Construct and apply confidence intervals for one-sided and two-sided hypothesis tests and interpret the results of hypothesis tests with a specific confidence level
two: [mu_hat +/- C(alpha/2) * sigma_hat / sqrt(n)]
one: [mu_hat - C(alpha/2) * sigma_hat / sqrt(n), infinity)
(-infinity, mu_hat + C(alpha/2) * sigma_hat / sqrt(n)]
Identify the steps to test a hypothesis about the difference of two population means
H0: mu1 - mu2= 0