Lars P. Syll

 [embedded content]

When I present this argument … one or more scholars say, “But shouldn’t I control for everything I can in my regressions? If not, aren’t my coefficients biased due to excluded variables?” This argument is not as persuasive as it may seem initially. First of all, if what you are doing is misspecified already, then adding or excluding other variables has no tendency to make things consistently better or worse … The excluded variable argument only works if you are sure your...

 [embedded content]

RCTs in the Garden of Eden Suppose researchers come to a town and do an RCT on the town population to check whether the injection of a green chemical improves memory and has adverse side effects. Suppose it is found that it has no side effects and improves memory greatly in 95% of cases. If the study is properly done and the random draw is truly random, it is likely to be treated as an important finding and will, in all likelihood, be published in a major...

On a winter’s day (personal)  [embedded content] Yes, indeed, looking out my library windows, the sky is grey, rain keeps falling, and spring seems to be far, far, away. Although it’s more than thirty years now since I was a student at the University of California, on a day like this, I sure wish I was there again …

Tony Lawson — en presentation En av de ledande metodologerna inom den ekonomiska vetenskapen i dag heter Tony Lawson. Denne engelske ekonom har i flera böcker på djupet undersökt och kritiserat de vetenskapsteoretiska och metodologiska fundamenten för den moderna nationalekonomin. Ekonomer uppvisar ofta ett svalt intresse inte bara för det egna ämnets idéhistoria, utan också för vetenskapsteoretiska reflektioner kring förutsättningarna för och antagandena...

Machine learning and causal inference  [embedded content]

Conventional thinking about financial markets begins with the idea that security prices always accurately reflect all available information; it ends with the belief that price changes come about only when there is new information. Markets are supposed to reflect new information quickly and efficiently, albeit with a few anomalies. In 2007, I interviewed over 50 investment managers mainly in New York, Boston, London, and Edinburgh. Talking to them I came to the conclusion that...

[embedded content] This one is for you — brothers and sisters, struggling to survive and risking your lives fighting for liberation. May God be with you.

Econometric causality and Simpson’s paradox Which causal relationships we see depend on which model we use and its conceptual/causal articulation; which model is bestdepends on our purposes and pragmatic interests. Take the case of Simpson’s paradox, which can be described as the situation in which conditional probabilities (often related to causal relations) are opposite for subpopulations than for the whole population. Let academic salaries be higher for...