“You want to see a nice, healthy, strong p-value, at least less than 0.01. Then you really start talking about something you want to put your money on.? — Victor De Gruttola, Harvard School of Public Health

Jon Cohen, who wrote a great essay for ReportingonHealth on covering HIV/AIDS, has a thought-provoking ScienceNOW Daily News article on a topic that has stymied many a trained health journalist: how to properly refer to p-values in stories. The article is no easy read, but it's well worth your time if you cover medical research.

Cohen interviews Victor De Gruttola, chair of biostatistics at the Harvard School of Public Health, to get his take. Here's how he starts his article:

Victor De Gruttola, the chair of biostatistics at the Harvard School of Public Health, is passionate about his p-values. That's why he was apoplectic last month when an esteemed colleague and prominent AIDS vaccine researcher spoke with him about the widely publicized results of the largest-ever AIDS vaccine trial. "The probability that this vaccine didn't work was only 4%," said his colleague, whom we will call Thor to spare from further embarrassment.

Most mere mortals would assume that was a reasonable interpretation of the results of the Thai trial, in which 51 out of 8197 people in the vaccine arm of the trial became infected with HIV, compared with 74 out of 8198 people who received a saline placebo shot. That translates to a difference of 31.2%, which led to a p-value of 0.04, just below the arbitrary but widely used statistically significant cutoff of 0.05. (Two other analyses of the data did not reach p <0.05, but that's a different statistical dilemma.)

It's also worth checking out AP medical writer Lauran Neergaard's ReportingonHealth essay on covering medical research. Have you seen good or bad examples of mainstream media reporting involving p-values? Share them in the comments below. You need to be a registered member of ReportingonHealth.org to leave a comment, so if you haven't joined yet, click here.It's easy, quick and free. You can follow us on Twitter, too, @ReportingHealth.