Posted by: TomA | 18 December 2007

The murky waters of econometrics

As part of my Masters program, I’m required to undertake a piece of econometric research. Having been interested in the academic debate over giving aid to developing countries, I set out to see if aid was/is effective in promoting growth (the main economic rationale for donors giving aid; setting aside the moral/ethical obligation of aid).

The econometric literature has seen heated debate, since the World Bank asserted that aid is only effective in a good policy environment; otherwise having no effect. This arguably led to fatigue amongst donor nations. The result: diminished aid flows in the new millennium. But isn’t aid good? Doesn’t it help the developed world progress their health and education systems, afford imports of improving technology, cope with natural disaster and generally improve welfare?

Well, econometrically, who knows. The department at Nottingham is adamant that it does help and have the econometrics to back it up. Yet, by admittance, finding the “correct” result is difficult.

Hang on a second… finding the correct result is difficult? Isn’t econometrics and statistics preached as truth in universities across the land?

My (decidedly crude) results hold true to this. Treating the data in slightly different ways can allow me to prove aid is associated with good growth, it is insignificant or associated with poor, even declining growth. Note the lack of a causal statement.

So my results, using data from a number of published studies (including in the holy grail of the American Economic Review) provide no conclusive evidence. This seems to be consistent – rarely is there any indication or discussion of this lack of robustness. As such,  mixed results suggests that you, as an economist, cherry pick those that tell the story you want to tell, and damn it with the truth.


Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s


%d bloggers like this: