[bostonpete]

That statement jumped out at me as ridiculous. Of course conceptions are up in those months if there is increased frequency of births 9 months later. That's not an "reasonable explanation" of the data so much as a restatement of it...

[aaronharnly]

Just to play devil's advocate -- not every conception results in birth, and it's not implausible that the P(birth|conception) might vary over the year. For example, if a first trimester in the winter were more likely to result in miscarriage; or if more unwanted conceptions resulting in abortion happened in spring (??).

But, yeah, I agree :)

[bostonpete]

Hmm, good point. Whether it's a reasonable assumption or not, I had unconsciously assumed the ratio of births to conceptions would be constant. You get an A for logic, I'll give myself a C... :-)