<p>^ Sure, but that’s just an argument against choosing graduation rate as a statistic of interest. You could pick whatever you want.</p>
<p>This is the difficult with analyzing correlates rather than trying to measure casual effects. The best way to do this would be to come up with some kind of instrument which predicts SAT scores but is not correlated with graduation rates. Then we can being to isolate the causal effect of SAT scores on graduation rates. Even then, we’d have to combine this with a fixed effects model to remove the different factors at each institution. </p>
<p>Measuring the effect of an institution on students is much more difficult, maybe impossible, in a causal way, based on this information.</p>
<p>“rogracer-
What do you mean when you say that some MIT students were truly incompetent? Socially incompetent? I find it hard to believe that any MIT students are incompetence although some may have underperformed relative to their ability.”</p>
<p>No, I mean incompetent as in you wouldn’t want to fly in an aircraft in which they performed the fatigue analysis. You’d never pick these people out from their SAT scores.</p>
<p>
</p>
<p>Agreed. This is interesting nonetheless, but the graduation rate correlation probably has more to do with the fact that high-score kids are more motivated and thus more likely to graduate from any institution. But, like CCers, they’re attracted to prestigious schools in droves, upping Harvard, etc’s graduation rates.</p>
<p>Of course, the fact that Ivies (excluding Princeton) have massive grad inflation may be part of the correlation as well–and the reason the tech schools see lower grad rates despite comparable scores.</p>
<p>Graduation rates are, by nature, endogenous to the schools themselves so it’s not a measure which is easily isolated.</p>