Happy birthday? An observational study

Background: Previous studies show contradictory findings on the relationship between birthday and deathday, in particular whether people postpone death until after their birthday. We examine the phenomenon in eight groups of famous people.
Methods: Birthday and deathday for the following groups were recorded: British prime ministers, US presidents, Academy Award best actor, best female actor, best director, Nobel Prize winners, Wimbledon men’s and ladies' singles winners, all from when records began. For each group, the difference in days between the deathday and birthday was calculated. Under the hypothesis of no association, one can expect the difference to have a uniform distribution. This is assessed using goodness-of-fit tests on a circle.
Results: All groups showed some departure from the uniform and it occurred around the birthday in all groups. British prime ministers, US presidents, Academy Award actors and directors, Nobel Prize winners and Wimbledon men show a ’dip' in deaths around the birthday. The length of the ’dip' varied between the groups and so they gave different p-values on different test statistics. For Academy Award female actors and Wimbledon ladies, there was rise in deaths before and after birthday. When Nobel Prize winners were subdivided into their categories, Science and Literature had a ’dip' around the birthday, but not other categories.
Conclusions: We conclude ’something' happens to deathday around the birthday. Some groups of famous people show a ’dip' in death rate around the birthday while for others, particularly women, the association is in the opposite direction.