Tuesday, August 19, 2008

The next thing is to inquire whether the saints are listening...

The empirical conclusion from this analysis is important. A little prayer does no good and may make things worse. Much prayer helps a lot.


If Jim Heckman says that, it's gotta be true.
So, either stop praying altogether, or pray 24/24, nothing in between helps...

PS. Andrew M. Greeley's letter attached at the end of Heckman's paper deserves praise on its own.

4 comments:

Anonymous said...

hi Sebone....well this is interesting...maybe meaningless but probably funny. ciao

Sebi Buhai said...

Ciao Siciliano,

"meaningless"> are you questionning the "accept on faith assumption"? :-)

I bet it's going to be the most downloaded IZA discussion paper, even without praying for that :-).

Anonymous said...

Absolutely hillarious. The old man wrote his best as yet. Guess it's related to the old fights with Angrist et al.

Sebi Buhai said...

With a reservation here: I don't think it's a particular "fight", rather the more general idea often claimed in papers that you simply assume the conditional density of an X given Y is of given form etc (eg., "effect of income on happiness" or "effect of income inequality on democracy"; you see where he's going) :-). In fact the end is the best, where he states that he conjectures such analysis might be extended to the more general case where X is not observed either :-).