Search interesting materials

Tuesday, October 06, 2009

2009 Economics Nobel Prize

We'll soon get the announcement. Here are a few possibilities, computed by Thomson/Reuters, using citation analysis.

If I had to vote, it would be a Taylor/Woodford prize.  For a sense of this work, see: link, link. While inflation targeting was invented in New Zealand based on the intuition of cleanliness in public administration, Taylor and Woodford had a lot to do with being able to think straight about it.

It's interesting to wonder how publicly visible citation data can be used to predict the Nobel prize outcome. One would want some kind of model which consumes citation data and comes up with an estimate of the Pr(Nobel prize). E.g. if one strong idea suffices (example: James Heckman) then it suggests certain people who will get through (example: Paul Romer). If they want you to build a broad literature (example: Robert Lucas) then that yields a different profile of those who will get through. Hmm, I can't come up with an example of another Robert Lucas. Such a modelling effort will yield insights on the usefulness of summary statistics of citation data such as the h-index and the g-index. As an example, it's easy to test which of the h index or the g index have superior predictive power in a model of predicting the Nobel prize.

For an analogy, it's easy to take firm data and fit an ordered probit model which predicts the credit rating. Once this is done, you're holding a black box which is able to look at firms, and come up with a real valued measure of credit risk. In similar fashion, once a model is estimated, which maps citation data and generates a real number from 0 to 1 (e.g. the probit latent variable), then it can be applied to a full database of all economists, and yield a measure of how Nobel-like each person is. This can be easily layered into Google scholar.

Most people in India think of Raghuram Rajan as being the first Indian-born economist who became the chief economist of the IMF. What is not widely appreciated is that in the class of economists of Indian origin who are younger than Amartya Sen, Raghu is the best set of papers, as measured by citations.

15 comments:

  1. "What is not widely appreciated is that in the class of economists of Indian origin who are younger than Amartya Sen, Raghu is the best set of papers, as measured by citations."

    The above statement is not true; even if you consider google searching as a measure of greatness. One would like to know the criteria employed by Ajay Shah for coming to the conclusion of "best set of papers".
    Arvind Panagariya has an equal number of citations (actually 5 more)and is definitely younger than Amartya Sen. Shall we call for Nobel Prize for Panagariya?
    Are we not forgetting some one senior with a huge body of scholarly work and lot more citations : like Jagdish Bhagwati.

    ReplyDelete
  2. Quickies - http://nobelprize.org/nobel_prizes/ calls it "Prize in Economics" whereas other disciplines have titles ... "Nobel Prize In ..."

    http://johnbtaylorsblog.blogspot.com/2009/09/crisis-failure-or-vindication-of.html doesn't accept the failure of Macro ..

    ReplyDelete
  3. Look Here for Panagariya citations...
    http://scholar.google.com/scholar?hl=en&num=20&q=author%3A%22A+Panagariya%22&btnG=Search&as_subj=bus

    ReplyDelete
  4. There has been a murmur in the press over the past year about considering N.N. Taleb (Black Swan fame) for the same. I do understand that number of citations/research papers may help a case, but still the contribution through promoting a new insight can help the case of certain nominees. What do you think regarding the same? I have read his books as a part of my curriculum (The Black Swan & Fooled by Randomness) and though Quants (including me!) may be skeptical with some of his observations, his thoughts do highlight certain prudence for the expectation of an unexpected change!

    ReplyDelete
  5. The author clearly has not the faintest idea how the Econ prize gets decided..... nothing to do with citations...

    ReplyDelete
  6. I dont know about Econ, but surely we got an Indian(alright an NRI) as a Chemistry Nobel Laureatte this time.

    Venki Ramakrishnan ;) His work was on ribosome structure and function ;)

    His lab page

    ReplyDelete
  7. Anonymous,

    I deleted your comment because you violated the rule of: "no personal attacks".

    ReplyDelete
  8. Ok Prof. That is a fair justification for your action

    Let me now rephrase my point without violating that rule.

    The answer that Prof. Shah has given to the question made by the first anonym commenter regarding criteria of reaching the conclusion on "best set of papers" is not adequate. The links he has given does not say any story by itself. In fact Raghuram Rajan has less citations compared to Prof. Jagdish Bhagwati even in google scholar citations provided. Prof. Shah, Please provide a better reply

    Naveen

    ReplyDelete
  9. Summing the cites of the top 5 papers at this url yields 8534 while summing the top 5 papers at this url yields 1573.

    1573 is very, very good. It is a great achievement. But it is not the sort of thing that one sees with Nobel laureates.

    ReplyDelete
  10. 1,000 citations or 1,000,000 citations, macroeconomics has disappointed us.

    Its funny - my Chemistry teacher would mix chemicals and show a reaction where the thing formed has some totally different color. Will economists ever get it if Economics is far from getting there. In fact its even wrong!

    ReplyDelete
  11. Twitter from Nobel Foundation

    says

    Elinor Ostrom is the first woman to receiveThe Sveriges Riksbank Prize in Economic Sciences in Memory of Alfred Nobel 2009 #nobel09

    ReplyDelete
  12. If citations are measure of greatness; then Luigi Zingales has 7016 citations of first five papers as per Prof. Shah's parameters and would be atleast as impressive as Raghuram Rajan and much better than Elinor Ostrom (Nobel Prize 2009) with 3702 citations.
    Even now Prof. Shah does not explain what he means by "Best set of Papers".

    ReplyDelete
  13. thank god for elinor ostrom!.finally a non math mumbo jumbo social sciences person gets it.happy that none of the mathwhizs came close.

    ReplyDelete
  14. Luigi is also a superb economist.

    The sentence from my blog post reads: "What is not widely appreciated is that in the class of economists of Indian origin who are younger than Amartya Sen, Raghu is the best set of papers, as measured by citations."

    So I'm looking in the class of Indian-born economists younger than Amartya Sen.

    ReplyDelete

Please note: Comments are moderated. Only civilised conversation is permitted on this blog. Criticism is perfectly okay; uncivilised language is not. We delete any comment which is spam, has personal attacks against anyone, or uses foul language. We delete any comment which does not contribute to the intellectual discussion about the blog article in question.

LaTeX mathematics works. This means that if you want to say $10 you have to say \$10.