STAT 1000Q Lecture Notes - Lecture 16: Null Hypothesis, Medical Test
19 Oct 2017
School
Department
Course
Professor
73
STAT 1000Q Full Course Notes
Verified Note
73 documents
Document Summary
Statistical hypotheses: unproven assertions about parameters of a distribution. Relates to what a value of a distribution is. Presumed to be true for the purpose of investigation. The null is tested against the alternate hypothesis. Presumed to be false, unless the data shows more significantly more consistent with the data than the h0. Example: a medical test for a specific disease. H0: presumptions that the patient does not have the disease. Ha: the patient does have the disease. Can be clinically insignificant at the same time. A procedure where data is collected that either supports or rejects the h0. Example: oil change services claim an average of 15 minutes. Get a sample of 50 customers to get a sample mean for comparison. Larger than 15 significantly, we reject h0 and accept ha. If close, do not reject h0, we would accept h0. M0 and p0 is what we think the true mean and proportions are if the h0 is true.
