STATS 2B03 Lecture Notes - Myocardial Infarction, Contingency Table, Aspirin
Document Summary
The chi-square distribution and the analysis of frequencies (3) 12. 4 tests of independence the above test of homogeneity in an r c contingency table is also a test of independence of the row factor and the column factor. H0: p1 = p2 = = pk is the same as h0: the row and column factors are independent. If h0 is not rejected, then we cannot conclude that the factors are independent. We can only conclude that there is not strong evidence of dependence. Russel"s paradox (not related to independence) suppose that we observe the following data: 325 had a heart attack had a heart attack. No aspirin group: this data suggest that aspirin increases the chance of a heart attack instead of reporting this, you could cleverly split up the subjects as follows. No aspirin group: this suggests that aspirin decreases the chance of a heart attack. Ha this also suggest that aspirin decreases the chance of a heart attack.