1855 — the birth of causal inference
from Lars Syll
If anything, Snow’s path-breaking research underlines how important it is not to equate science with statistical calculation. All science entail human judgement, and using statistical models doesn’t relieve us of that necessity. Working with misspecified models, the scientific value of statistics is actually zero — even though you’re making valid statistical inferences! Statistical models are no substitutes for doing real science. Or as a German philosopher once famously wrote:
There is no royal road to science, and only those who do not dread the fatiguing climb of its steep paths have a chance of gaining its luminous summits.
We should never forget that the underlying parameters we use when performing statistical tests are model constructions. And if the model is wrong, the value of our calculations is nil. As ‘shoe-leather researcher’ David Freedman wrote in Statistical Models and Causal Inference:
I believe model validation to be a central issue. Of course, many of my colleagues will be found to disagree. For them, fitting models to data, computing standard errors, and performing significance tests is “informative,” even though the basic statistical assumptions (linearity, independence of errors, etc.) cannot be validated. This position seems indefensible, nor are the consequences trivial. Perhaps it is time to reconsider.
Leave a comment
—– look inside —– $5.94 / $20.00
—– look inside —– $4.90 / $8.00
—– look inside —– $15.99
—– look inside —– $5.99 / 12.99
—– look inside —– $5.93 / $12.99
—– look inside —– $4.97 / $9.90
—— Ugarteche, Puyana and Madi ——
Gerson Lima / Maria Alejandra Madi
Edward Fullbrook and Jamie Morgan
————— Michael Hudson ————–
Maria Alejandra Madi / Jack Reardon
————- Edward Fullbrook ————-
—————— Steve Keen —————–
————— Richard Smith —————
————– Gustavo Marques————
– Victor Beker and Beniamino Moro –
————– Lars Pålsson Syll ————-
—————– Stuart Birks —————-
Edward Fullbrook and Jamie Morgan
———— Armando Ochangco ———-
Shimshon Bichler / Jonathan Nitzan
————— Mauro Gallegati ————–
————— Herman Daly —————-
————— Asad Zaman —————
—————– C. T. Kurien —————
————— Robert Locke —————-
Real-World Economics Review Blog 
This blog simply states the truth. Unless the model being tested is valid, nothing useful is to be found. The only way to determine what is required is an analysis from first principles. Then the relationships being used must conform to the quantity calculus. Economists continually fail to recognise this fact. The next failure is understanding how hypotheses are to be rejected. They fail to reject what should be rejected even when physical scientists points this out. I have repeatedly stated there is no orthodox nor heterodox quantitative analysis which passes the requirements of the quantity calculus. It would appear that virtually no one seems to recognise this fact. This leads to Lars Syll repeatedly talking about self evident truths such as this blog and stopping short of discussing what really matters — how well do other hypotheses describe reality.
Reiss (2011) states:
“It is not economic theory as such that is what is wrong with economics, but rather a certain form of reasoning that resembles theorising but is in fact far from it. I take genuine scientific theories such as Newton’s, Darwin’s or Einstein’s (or even Marx’s or Freud’s, if we suppress empirical doubts for the moment) not only to provide a conceptual framework within which to think about problems of interest, but also a small number of explanatory hypotheses that can be used over and over again in the explanation of a wide range of phenomena. Genuine theories are surprising and counter-intuitive in which they show that phenomena, once thought to be unrelated, in fact share a common origin. Modern mainstream economics does nothing of this kind.”
This is a cogent description of what valid theory will be like.
Reference:
Reiss, J. (2011). Theory, generalisations from cases and methodological maxims in evidence-based economics: Responses to the reviews by DiNardo, Guala and Kincaid. Journal of Economic Methodology, 18, 93–96. http://dx.doi.org/10.1080/1350178X.2011.550125
For people who enjoy metaphors, the John Snow story is a good one. We observe that these people over here are becoming poorer and sicker and they aren’t living as long. But over there we see a few people who are becoming richer and richer, buying houses and airplanes and yachts, having plenty of food and going to the best doctors when they need to. What’s this in the middle, though? It’s an economic system that pumps money in one direction – toward the rich people – while at the same time pumping inequality, deprivation, disease, and malnutrition in the other direction. The pump is monopolistic finance capitalism working exactly as it is designed to work, supported by legions of smart economists and seemingly well-intentioned politicians. The solution? Remove the handle of the pump!
“The solution? Remove the handle of the pump!” Or reverse the polarity of the carrier (the value of money) so the pump pumps “inequality, deprivation, disease, and malnutrition in the other direction”, i.e. to the rich who are accumulating it. Instead of thinking of money having the value of the goods we buy with it, think of it as a limit to our own credit worthiness, which if spent has to be earned, e.g. by selling off what we have acquired, and if not will in due course attract the evils now afflicting those unfortunate enough to be “unemployed”.
All models are “wrong”. Some models are consistent with past data. That doesn’t make them right but it might make them useful. If they aren’t consistent with past data, they are unlikely to be useful. Friedman and Schwartz built the theory of monetarism on the assertion that the velocity of circulation of money was stable, which they claimed was empirically the case (there was no purely theoretical reason for supposing it to be so). Hendry and others used econometrics on US data to show that the velocity was not only not stable, it wasn’t even mean-reverting. It was, statistically speaking, a random walk. There were other reasons to reject monetarism, such as the endogeneity of broad money, but empirical testing was the coup de grace.
If cholera had continued after Snow removed the pump handle he would have had to think again. In the absence of such decisive means of testing most hypotheses in social studies we have to do the best we can. Statistics has a role; if you don’t want to call that science, fine. Call it what you like.
My model is the arrow will fly straight enough to hit the target. And if an enemy soldier, to kill that soldier. All this elitism is nauseating. “There is no royal road to science, and only those who do not dread the fatiguing climb of its steep paths have a chance of gaining its luminous summits.” Except, of course you attended MIT or Cal. Tech, have a large grant from an even larger corporation, and all the data and testing assistants needed. In other words, people have been doing science long before MIT and Cal. Tech, large grants, and “big” data designs. Armorers making arrows and bows, farmers planting and harvesting crops, mechanics building windmills and water wheels to grind grain, etc. all were scientists. Let’s put the praise and applause where it belongs. With those who invented, installed, and made function the devices and actions that directly made the lives of themselves and many others safer, happier, more secure, and more successful. “Big” science has since the end of WWII been in the hands of government or corporate power structures more interested in control and/or profits than any of these goals. In the 1950s Jonas Salk was an independent scientist searching for a polio vaccine. Funded by the March of Dimes and similar charities, his research facilities were small but effective. In today’s world there is no place for scientists like Jonas Salk. That’s demonstrated no more clearly than in the case of Mark Zuckerberg. Zuckerberg claims to be a scientist. A scientist whose digital inventions might be beneficial and useful to people but for the fact of Zuckerberg’s all-encompassing pursuit of wealth (current net worth $75 billion). Is what Zuckerberg provides the public worth the price they pay, in both money and interference in their daily lives? No. It’s not just bad for societies, it’s bad for science.