That article has this interesting statistic and some ideas for further research:

“The USA Math Olympiad (USAMO) only had 19 out of 230 women when I took it in 2010, a meager 8.3 percent.”

As a follow up to that statistic I looked up the scores from the 2015 American Invitational Mathematics Exam (the “AIME”, which is the contest students take to qualify for the USAMO) here:

and found similar statistics to the ones quoted for the 2010 USAMO. For the 2015 AIME, there were 25 female scores of 10 or above and 230 male scores of 10 or above (and 30 scores of 10 or above with gender unknown).

One data point, I know, but it seems that there’s not been much change in the gender distribution of the top scores in the AMC contests since 2009.

The only research I’ve seen on the AMC contest scores is this fascinating paper from MIT’s Glenn Ellison and Ashley Swanson in 2009:

This paper mentions an astonishing statistic for the top-scoring girls in the US:

“Whereas the boys come from a variety of backgrounds, the top-scoring girls are almost exclusively drawn from a remarkably small set of super-elite schools: as many girls come from the top 20 AMC schools as from all other high schools in the U.S. combined.”

So, in addition to some of the research ideas mentioned in Boppana’s article, I think a productive area of research into the gender imbalance in math would be digging into that statistic a bit more. What exactly is happening at these 20 schools? I doubt it is one simple thing, but these 20 schools sure seem to be doing something worthy of further study.