The love doctor himself, Kevin Denny, has some unpleasant educational arithmetic:

Given the major pressures on the public finances and hence on public spending on education, the question of class-size is likely to rear its ugly head again. We don't have good evidence for Ireland though there is some good potentially data. So what does it tell us - at least at first blush?

Using PISA data for Ireland I show a kernel regression of the students (15 year olds) against class-size. The results show that as you lower class size from 40 to about 35 there is a higher score- as you might expect. After that however, its down-hill all the way: smaller classes are associated with worse scores. This is actually robust to inclusion of school effects and various other controls. In work in progress with a colleague it even seems to be robust to controling for endogeneity (using two distinct identification strategies).

via Geary Behavioural Economics Blog: Some unpleasant educational arithmetic.

2 Responses to “Some unpleasant educational arithmetic”

1. kevin denny

   23/03/2010 at 12:40 pm

   Thanks for the "hat tip" though I can assure your readers my expertise on matters of love has been greatly exaggerated (& yes, by myself).
   The upward sloping relationship shown (i.e. students doing better in bigger classes) is replicated if one looks at other countries - I have checked this for a bunch of countries in the PISA data. So there is something going on though what I am not sure. It could be a pure statistical artifact whereby schools or parents send the weaker students to smaller classes. I have reason to believe that this is not the explanation but it would take too long to explain. Our paper should make this clearer.
   Perhaps the graph illustrates the need for a much more detailed analysis of the Irish data on this topic given how important it is. It is not good enough to rely on intuition or prejudice or a sketchy knowledge of the international evidence.

2. Stephen

   23/03/2010 at 12:49 pm

   I'd highly doubt there's a statistical artifact explanation, Dr Lurve, because of the shape of the curve more than anything else, but also because there must be more going in the classes than less students implies higher grades. Also, if they are rational, the parents should send the weaker students to larger classes, no?

   Clearly there's loads of work to be done on this, but from this picture alone, the class size story gets destroyed, especially from a teacher's wage-maximisation/bargaining point of view.