Friday, June 06, 2008

Empiricism Gone Mad: or, how I learned to love regression analysis

A recent post of mine over at the Blog at Mises.org.










Empiricism Gone Mad: or, how I learned to love regression analysis



Under the Weather: Health, Schooling, and Economic Consequences of Early-Life Rainfall is a recent offering from the National Bureau of Economics Research.

Who would have thought that the rainfall in your birth-year and birth-location determines (inter alia) your lung capacity, height, final education level, etc? Of course, there is the big caveat that this only holds for women born in rural Indonesia between 1953 and 1974. Regardless, it's now empirical fact and ready to guide public policy -- you understand, the rainfall gap and all.

The best I can assume is that authors Sharon L. Maccini and Dean Yang found the only remaining data sets that had not yet been correlated and had at it. Or, maybe they simply had government grant dollars to consume. Either way, their main contribution is additional proof that empiricism is nonsense.

8 comments:

Paul said...

Jim:

Like you, I don't put too much faith in correlation analyses as a technique for providing answers, but I do think they can help us form better questions and set a direction for further research.

I think of science and mathematics as being the one of the ways we get a glimpse into the majesty of God. The closer we get to the Truth, the simpler the language becomes. E=mc2 is perhaps the most beautiful scientific revelation in our history.

I think you might even be able to say that in any field, the 'quality' of the science is defined by how simple the core equations are. Our goal should be to throw away terms in equations we hold dear.

Eventually it all resolves to "God = Love"

Jim Fedako said...

Paul,

Thanks for the comment.

The post is on empiricism as the epistemological foundation of one's belief system. Empiricism is not empirical research.

There is nothing wrong with looking at data. The issue is whether data trumps theory -- whether data is your belief system.

Like you -- I am assuming your view here, I look to the Bible as my foundation. I then add in the a priori truths of Austrian economics. This is my foundation.

Should some correlation of disparate data sets show otherwise, I know that the analysis of the data, or the data, is flawed.

By way of example: Government economics data can never trump the truths of Austrian economics. The government data and the analysis of that data is inherently flawed.

Some folks have no foundation and simply bob between positions based on the latest "research." That is the essence of empiricism.

Anonymous said...

I would like to add one more equation to God=Love..One that I have had the pleasure of the personal experience.
children=meaning of life

Anonymous said...

I would like to add one more equation to God=Love..One that I have had the pleasure of the personal experience.
children=meaning of life

Anonymous said...

I would like to add one more equation to God=Love..One that I have had the pleasure of the personal experience.
children=meaning of life

Anonymous said...

I like how if the data goes against your beliefs, the data must be wrong.

It must be difficult to go through life with your eyes closed, comforting but difficult.

Jim Fedako said...

Ah, yes ... the empiricist. Intellectually formless, bouncing from this to that, grabbing the latest fad as reality.

You would do better reading the NBER website. They have a lot of contradictory reports to read -- you know what I'm talking about, report 1 claims A while report 2 claims not-A.

Hold your head so that it doesn't spin to fast. Of course, your heads is likely no longer attached and not an issue.

IMM said...

Anonymous is dreaming if he (she) believes that anyone can be purely empirical and without a paradigm through which to interpret data.

Data is absolutley meaningless without a theoretical framework through which to view it. If you don't think you have one, you do, just not an informed or carefully chosen one.

Anonymous is looking at everything through the lens that all data has inherent meaning and doesn't require prior beliefs to make sense of it. that is itself a prior belief, like it or not.

Jim, on the other hand, recognizes that all data requires prior belief to be interpreted and to have meaning, and he has set out to discover what the correct theoretical framework is, and chosen consciously to adopt it and interpret data through that lens. Seems a much more scientific way to me.