Table 2 We compared the difference in mean AUC values between the various datasets using a t test. The datasets consisting of people born after 1930, 1940, and 1950 all showed significant differences with the corresponding random control. Those three datasets also showed significant differences between the mean AUC and 0.5. The three random controls did not show a significant difference between the mean AUC and 0.5, as expected. An AUC value of 0.5 represents a random classification test, one in which the algorithm is no better than guessing
p value of t test | ||
|---|---|---|
1930 data | 1930 random | 2 · 10−11 |
1940 data | 1940 random | 1 · 10−9 |
1950 data | 1950 random | 1 · 10−4 |
0.5 | 1930 data | 3 · 10−14 |
0.5 | 1940 data | 4 · 10−13 |
0.5 | 1950 data | 3 · 10−4 |
0.5 | 1930 random | 0.1 |
0.5 | 1940 random | 0.4 |
0.5 | 1950 random | 0.08 |