Appendix

STATISTICAL TEST OF US PRESIDENTS

TO SEE IF THE SUPPORT that the data appears to give LFT is statistically significant, its key hypothesis must be reformulated into a mathematically equivalent statement. The hypothesis becomes as follows: Unfiltered presidents have a mean consolidated rank that differs from the mean consolidated rank of all presidents by an amount significantly greater than the amount by which Filtered presidents have a mean consolidated rank that differs from the mean consolidated rank of all presidents. The null hypothesis is that the mean consolidated ranks for Unfiltered and Filtered presidents are no different in variance.

Distance from the mean should be tested using absolute variance (ABS). Ranki is the normalized ...

Get Indispensable now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.