There are lots of interesting papers in recent editions of the Journal of Human Resources but this one caught my eye:
Rees, D. I., and J. J. Sabia. 2011. “The Effect of Migraine Headache on Educational Attainment.” Journal of Human Resources 46(2): 317–332.
Despite the fact that migraine headaches are common and debilitating, little is known about their effect on educational attainment. Using data drawn from the National Longitudinal Study of Adolescent Health, we estimate the relationship between migraine headache and three outcomes: high school grade point average, the probability of graduating high school, and the probability of attending college. Our results provide evidence that migraine headache negatively impacts human capital accumulation. The relationship between migraine headache and educational attainment is explained, in part, through its effect on school absences and the respondent’s self-reported ability to pay attention in class and complete homework
Showing posts with label health research. Show all posts
Showing posts with label health research. Show all posts
Wednesday, March 9, 2011
Friday, February 11, 2011
How not to do Instrumental variables
Instrumental Variable estimation, Generalized Method of Moments and related techniques are part of the standard toolkit for applied economists. They are also increasingly used in other fields such as health.
What everyone knows, or should know, is that while one can think of these models as a two stage process this is not actually how you do it. But this paper which looks at how systolic blood pressure depends on anti-hypertensive drugs in Japan, published in the Bulletin of the World Health Organization 2008, gets it badly wrong. As they note, a simple regression of blood pressure on medication is likely to get a positive slope so you need to instrument or do something.
They estimate a logit and then stick the predicted values into an OLS model. Aside from the identifying assumption (which isn't discussed & looks pretty dodgy to me), this is not IV as usually defined and it is not clear that the estimate is consistent or that the standard errors are correct. The model also includes controls for exercise but these are also likely to be endogenous but this is ignored.
What everyone knows, or should know, is that while one can think of these models as a two stage process this is not actually how you do it. But this paper which looks at how systolic blood pressure depends on anti-hypertensive drugs in Japan, published in the Bulletin of the World Health Organization 2008, gets it badly wrong. As they note, a simple regression of blood pressure on medication is likely to get a positive slope so you need to instrument or do something.
They estimate a logit and then stick the predicted values into an OLS model. Aside from the identifying assumption (which isn't discussed & looks pretty dodgy to me), this is not IV as usually defined and it is not clear that the estimate is consistent or that the standard errors are correct. The model also includes controls for exercise but these are also likely to be endogenous but this is ignored.
Wednesday, January 5, 2011
Special Issue- Positive Psychology & Health
Subscribe to:
Posts (Atom)