November 25, 2009
You may have heard the flutter over UNAIDS’s report showing 17% reductions in HIV prevalence in sub-Saharan Africa. Sounds like good news all around, right? Well, here are brief thoughts on a few concerns i have about those figures.
i haven’t read the methods for the estimation closely, but it’s highly probable that some shifting population dynamics may be part of the story (e.g., recent declines in fertility – albeit modest – may be reducing the number of susceptibles sufficiently to shift the population structure enough to appear like a reduction when it’s not really one; similarly i don’t know how shifts in AIDS-specific mortality, have been accounted for either).
Perhaps more problematically for these estimates, given things that i have encountered personally in field work in Malawi, is the fact that those who know they are positive are more likely to refuse additional testing in the future. And with the – again, albeit limited – uptick in testing in many countries in SSA recently, the declines may be in part reflecting those refusals more than an actual drop in prevalence (see dadakim for more on this point).
i’d prefer to not always play the pessimist, i just think that this one should be read a bit cautiously.
2 Comments | Uncategorized | Tagged: bias, hiv, population estimation, SSA, UNAIDS | Permalink
Posted by jimi adams
October 9, 2009
While hanging out at Columbia the past couple of years, i was comforted to realize that i wasn’t alone in my lack of enthusiasm for p-values. In fact, while some folks in some disciplines are completely infatuated with them, did you know there are others out there that dismiss them? i mean, entirely!? [removes tongue from cheek]
While it might be an overstatement to suggest that the variety of headlines that accompanied the news of the HIV vaccine trial in Thailand claimed that “AIDS is now a disease of the past,” it really wouldn’t be stretching the tone of some of those headlines too far. Some people really did seem to think this was the breakthrough we’d been waiting for. That is, those people who focused solely on the p-values. E.g., from one of the NYT pieces on it “Although the difference was a mere 23 people…it was statistically significant.”
But what most people seemed to fail to pick up on was the very next part of that sentence – Read the rest of this entry »
4 Comments | Uncategorized | Tagged: hiv, media, significant, trials | Permalink
Posted by jimi adams