jump to navigation

RAND wrong October 19, 2007

Posted by ocmpoma in : economics , trackback

In case you couldn’t tell by the all-caps, I’m not referring to Ayn, but to the well-known (at least among health care / econ circles) RAND study from the 80’s. The study itself is a fairly big deal, here, for example, Robin Hanson at Overcoming Bias says that “[i]f you remember only one medical study, it should be the RAND health insurance experiment.”

Today both Assymetrical Information and Marginal Revolution point out a possible (and serious) flaw in the study: not accounting for those who ‘dropped out’. It seems that people with serious medical problems might have dropped out of the study, seriously skewing the results.

It seems to me that the error is sufficiently serious and also sufficiently elementary that it would require a fairly high degree of incompetence to make it; if it’s deliberate, well… so much the worse. So I’ll be snooping around over the next few days to see if anything turns up indicating that the drop outs don’t effect the study significantly, as the comments at MR seem to indicate is the case…

Tags for this article:

[?]

Comments»

no comments yet - be the first?