STATS 2B03 Chapter Notes - Chapter 9: Variance, Aspirin
Document Summary
*this should only be used if x1 5, n-x1 5, x2 5, n-x2 5 (ie. the number of (cid:862)successes(cid:863) a(cid:374)d (cid:862)failures(cid:863) i(cid:374) each group is as least (cid:1009)(cid:895) Example i(cid:374) the physicia(cid:374)"s health study (cid:1005)(cid:1005),(cid:1004)(cid:1007)7 physicia(cid:374)s took (cid:1007)(cid:1006)(cid:1009) (cid:373)g aspiri(cid:374) a(cid:374)d (cid:1005)(cid:1005),(cid:1004)(cid:1007)(cid:1008) took a placebo every other day over a 10- year period. 104 people in the aspirin group had a heart attack and. 189 people in the placebo group had a heart attack. Use = 0. 01. where p1 is the probability of heart attack for the aspirin group and p2 for the placebo group. Reject h0 if z > z /(cid:1006) or z < -z /(cid:1006) Reject h0 since -5< -2. 575 p-value (back of index card) = 2x area to the right of |z| If h0 is true (if aspirin has no effect), then it is extremely unlikely (probability < 0. 0002) to get such a big difference in the number of heart attacks between the two groups.