Part 2 of a series on risk; see part 1 here
A subtle point that I have made elsewhere is that the less sure we are of the outcomes of a development program, the more we should diversify. This is the reason we diversify our investments for ourselves, after all, so why don’t we diversify our investments for others?
Again, I stress that this is a very minor point, because any individual does not need to diversify if, across many individuals, there is already a lot of diversification. Still, it’s worth mentioning because the risk and uncertainty that underlies development programs’ expected outcomes is often glossed over.
A minor criticism of GiveWell (in addition to previous more substantive comments here) relates to this. They recommend only three charities, as they rightly see that there are opportunity costs to giving – we have limited funds to give, so we had better give them to the most effective charities. But, under risk, the most effective option is a diverse bundle. Again, I don’t think this is a major issue, since across individuals there is ample diversification. I just would prefer more honesty about it because I think it really does give the wrong impression about how much we know.
What is more important as an issue, and very neglected in the literature, is the diversity of effects a particular program might have. This comic explains it well. As the world develops more and more, you can easily imagine that the mean effect for a number of programs might go to zero. We need to start paying more attention to the distribution. Here, too, is where meta-analysis can help.