# Talk:Econometrics

WikiProject Economics (Rated C-class, Top-importance)
This article is within the scope of WikiProject Economics, a collaborative effort to improve the coverage of Economics on Wikipedia. If you would like to participate, please visit the project page, where you can join the discussion and see a list of open tasks.
C  This article has been rated as C-Class on the project's quality scale.
Top  This article has been rated as Top-importance on the project's importance scale.

This is a talk page. Please respect the talk page guidelines, and remember to sign your posts using four tildes (~~~~).

This article needs a section on the history of these methods — Preceding unsigned comment added by 77.202.83.46 (talk) 17:43, 15 January 2013 (UTC)

## Measurement Definition

People from the social sciences, econometrics, experimental psychology, psychometrics and other fields of measuring humans and human activity may want to provide input on the "measurement" article in Wikipedia. The current form of the article on measurement seems to exclude from measurement anthing other than "ratios of physical quantities" as it is used in the narrower field of metrology. You may want to provide some input on that.Hubbardaie (talk) 14:55, 2 May 2012 (UTC)

## Far too complex

I tried to add a simple overview for younger students as so far it's pretty complex!!! —Preceding unsigned comment added by 62.30.156.106 (talk) 17:16, 13 June 2008 (UTC)

I edited this post (as above - which got removed) a while back and again it has descended into being edited by people *who think* think know about econometrics.... GIVE A SIMPLE EXPLANATION TO EARLY STUDENTS. By editing the article in the manor you are, you're showing yourselves up and helping no one - let least those who are looking for a SIMPLE overview. —Preceding unsigned comment added by 62.30.156.106 (talk) 18:19, 25 June 2008 (UTC)

## Criticism?

There are plenty of critics of econometrics and its failure to model many aspects of economies. Why is there no section on criticism? —Preceding unsigned comment added by 74.39.212.101 (talk) 04:40, 4 November 2007 (UTC)

What you're describing is a failure of economic theory, not econometrics, to completely describe all economic events. Econometrics is simply a set of statistical tools used to analyze the data. Wikiant 13:40, 4 November 2007 (UTC)

I disagree. Nassim Nicholas Taleb's criticisms in "The Black Swan" and Edward Leamer's criticisms in "Let's Take the Con Out of Econometrics" (http://www.jstor.org/pss/1803924) would be quite appropriately summarized in a criticism section on this article. Lippard (talk) 04:18, 2 June 2008 (UTC)

I think the above comment is correct. It has many problems, one for example the ever constant believe that time series are stationary! —Preceding unsigned comment added by 62.30.156.106 (talk) 16:57, 13 June 2008 (UTC)

There is no ever constant belief that time series are stationary (see the many econometric tools that exist to deal with non-stationarity). Wikiant (talk) 21:50, 21 October 2010 (UTC)

I believe that there should be a section on criticism, of which one should definitely be a comment on the professions reliance on the assumption of normality in the past. However, this should be balanced by showing that many of the results that are relied on t-tests etc do not appeal to normality of residuals but to various central limit theorems. As for the stationarity argument, I think the article could do with some links to, for example, time series analysis and unit roots. Mts202 (talk) 11:45, 5 July 2008 (UTC) Matt

You are confusing the profession for the discipline. Econometricians may apply econometric techniques that assume normality to data that are non-normal. That isn't a criticism of econometrics, but a criticism of the econometricians. Wikiant (talk) 21:50, 21 October 2010 (UTC)

I removed the subsection on Taleb, for many reasons. Taleb's book is not a refereed source. One scholar's particular criticism does not comprise a body of thought sufficient to warrant inclusion in an encyclopedia article. Taleb's criticism is far-reaching, applying to many areas of quantitative science, not just econometrics. Finally, the paragraph itself included no useful information on what Taleb's criticism actually is: referring to the Lucas critique as a criticism of econometrics seems bizarre, given Lucas is an econonometrician and his Critique is taught in every first-year graduate macroeconomics course. If there is to be a "criticism" section, it should focus on a collection of papers in the peer-reviewed literature (Leamer, Freedman, McCloskey, etc), not one scholar's scattershot remarks in a book. Sked123 (talk) 20:04, 1 August 2008 (UTC)

Fair enough. II | (t - c) 20:15, 1 August 2008 (UTC)

Those users calling for such a section are quite right. The absence of one in this article is one of the worst examples of bias I've ever come across on Wikipedia. To the user above who said that such criticisms are irrelevant because it solely consists of statistcal tools, that's the whole point: critics claim that for all they may enable one to push numbers around so as to generate the results predicted by the models, the exercise is ultimately futile because the results aren't borne out in reality. It's like having an article on the Klingon language that omits all mention of the fact that the species doesn't actually exist.

For the sake of Wikipedia's credibility, someone needs to fix this, and sharpish. Lordrosemount (talk) 17:29, 21 October 2010 (UTC)

## Content

Going along the lines of the previous editor, econometrics is not mathematical economics (as falsely claimed by the page), nor is it statistics. Mathematical economics seeks to use deterministic methods and is generally axiomatic in nature. Econometrics tends to be empirical in nature and is by its very nature stochastic (though one could say it accepts the output of mathematical economics as an input, providing a theory-based approach to statistics).

I wanted to add some content to the introduction that differentiates econometricians and economic statisticians but I am unsure where to put it. The main difference is the economic statistician does not perform statistical tests upon the data to verify economic theory, only collects it.

I might go into detail about the 4 main components of econometrics (economic theory, economic statistics, mathematical statistics, and economic theory) how they make up econometrics, and how they are different from econometrics.

I don't think it matters too much where you put the differences, since it can always be moved. Just choose somewhere that makes sense for you. Expanding the article sounds like a good idea. -- Jrincayc 15:01, 4 Feb 2004 (UTC)

Good points. We also need some discussion of econometric models, what they are, how they are constructed, and how they are used for prediction and policy simulation. Let me think about how to do that. Any suggestions -- F. Gerard Adams (—The preceding unsigned comment was added by 209.6.125.23 (talk) )

The main page should atleast give links to some of the main ideas behind econometrics and regression anaylsis, such as Guass-Markov, Method of Moments, Logit, Probit, Tobit, Standard Errors, and Heteroskedasticity... and they should become articles under econometrics... -- LG (—The preceding unsigned comment was added by Leigao84 (talkcontribs).)

Remember WP:RS - a definition of Econometrics in a dictionary would help wonderfully with the opening paragraph.
Btw, I added something from the first issue of Econometrica... --Sumple (Talk) 06:47, 3 April 2007 (UTC)

I started an edit with the aim of trying to find a clearer example. I began a list of other methods that is pretty incomplete, but I think that a list would be helpful. EconProf86 01:45, 9 July 2007 (UTC)

It is true that a bit of learning is dangerous. Economics is a study started way before BC and Econometrics is a science which came centuries after. Econometrics is a tool which could be used in some Economical fields to produce formulas and charts to simplify education and work. The relationship would be exactly like Mathematics and Algebra. Economics has to be understood quiet well before people start commenting. —Preceding unsigned comment added by 80.227.86.225 (talk) 16:45, 26 July 2010 (UTC)

## Justification of equation

$lnY=-8.4009+0.6731lnX2+1.1860lnX3$

My question is that -8.4009 it is an intercept or not and why? —The preceding unsigned comment was added by 203.81.192.92 (talk)

It is a log-linear model and ln0,00022466=-8,4009 so it is an intercept.Soulviver 23:29, 30 April 2007 (UTC)

## Er....

I'm sorry, I can't understand a word of this article. Any chance of a simpler introduction? Adam Cuerden talk 02:27, 14 March 2007 (UTC)

## Rewrite

There need to be a major rewrite to the article. I've posted a link under Wikipedia talk:WikiProject Economics for it.Leigao84 22:03, 8 May 2007 (UTC)

## Difference between applied statistics

I took out the line about difference between statistics and econometrics from the intro and the reference to Granger causality.Leigao84 22:03, 8 May 2007 (UTC)

## Econometrics Packages

The list of econometrics packages is a bit ad-hoc -- several of the packages listed here are relatively minor in terms of importance to the field, and others (such as LIMDEP) that have well-established and strong user communities among econometricians are missing. Some of the packages listed here are more popular for teaching than for research, or are not particularly popular among econometricians at all. I didn't edit the list, however, as I don't think my judgment of what should be listed here (and in what order) is necessarily any more objective than anyone else's. My list would definitely include STATA, SAS, LIMDEP, SPSS, TSP, SHAZAM, eVIEWS. I would also include mathematical programming languages that are widely used by econometricians (even if they're not quite the same as the "canned" statistical packages), such as GAUSS, R, S, and MATLAB. Can anyone suggest criteria for this section? 68.148.229.84 21:54, 6 June 2007 (UTC)

I edited the list a bit, and omitted the packages that I didn't believe that econometricians used (in my experience as an econometrician). Some of the packages listed were obsolete. I thought sorting the packages might be helpful as well. I may have editted too deeply, however. EconProf86 01:42, 9 July 2007 (UTC)

TSP has been added. After providing econometric software user support for many years in a 150 person economic research institute, I conclude that TSP has been very well designed and is not obsolete. I agree with the 6 June 2007 posting above that it should be included in the list. Arie ten Cate (talk) 20:44, 10 January 2008 (UTC)

## Simple Example too complicated

It's my belief that a log equation is not simple to a general audience. Why not use the MPC? Burkander 02:04, 31 October 2007 (UTC)

## Logarithms and Utility

A disclaimer: I am not an econometrician. However, I believe the use of logarithms in econometric models has little to do with standard uses of logarithms, i.e. to convert multiplication into addition, and lots to do with the shape of a logarithmic curve, i.e. convex and monotonic. This is the shape needed to describe typical Utility functions, whereby increasing availability of a dependent variable (e.g. income) produces increasing utility to the consumer (e.g. happliness) that are reasonably described by a convex monotonic relationship. In plainer terms (I hope!), an increase in income produce increases in happiness, but such that the rate at which happiness increases reduces for larger incomes. Logartihmic curves look that way, so are a convenient utility function. P.r.newman (talk) 09:21, 3 April 2008 (UTC)

One reason for the use of a log-linear functional form is that it provides direct estimates of elasticities ie, you can just read the estimated parameter and that gives you an estimate of the income elasticity of demand, or whatever. Matt —Preceding unsigned comment added by Mts202 (talkcontribs) 11:49, 5 July 2008 (UTC)

Dude, I scored 3.29 log(t) utils making out with my girlfriend last night, where t was the duration of the makeout session in seconds. But seriously, there are an infinite number of monotonic convex functions. Out of this infinite set, 0% of the functions are logarithms. So there is a 0% chance of log being the correct choice. log might be adequate for some purposes. Doubledork (talk) 21:36, 6 November 2009 (UTC)

## Learned societies

Would it be possible to add a list of the main learned societies for econometrics? I am looking to resolve a red link in the article on Nikolay Fedorenko. Thanks. Itsmejudith (talk) 16:43, 3 July 2008 (UTC)

that says econometrics is bullshit

"The term ε is a random variable representing all other factors that may have direct influence on wage. The econometric goal is to estimate the parameters, β0 and β1 under specific assumptions about the random variable ε."

Please. VTNC (talk) 02:09, 4 October 2008 (UTC)

## "Econometrics"?

What a strange name. If I write "log(chance_of_cancer) = A * cigarettes smoked + B * asbestos snorted + C * days spent sunbathing", is that called "healthometrics"? If I write "log(bogeys) = A * lightning bolts + B * gopher holes + C * funny socks", is that called "golfometrics"? Doubledork (talk) 21:29, 6 November 2009 (UTC)

All philological abominations (including “econometrics”). The word “hygieinometrics” could stand where you propose “healthometrics”. There's no Classical Greek word for “golf”, but “moromicrosphairometrics” might work. —SlamDiego←T 20:19, 11 January 2010 (UTC)
Metrics means measurement, econo- is short for economics. Put them together and you get measurement of things relating to economics. Clear enough for anyone with a bit of common sense, Doubledork is just being difficult and attempting to be funny. — Preceding unsigned comment added by 80.170.189.51 (talk) 13:30, 5 December 2011 (UTC)
Yes. The nick tells it all. Of course for instance Ronald Fisher, one of the celebrated scientists of the 1900s, was just a funny guy playing with funny things, identifying himself as a biometrician and all. — Preceding unsigned comment added by 83.150.88.127 (talk) 13:04, 12 May 2013 (UTC)

I'm not sure how to correct it, I've just created a login to make this comment, but this page has been vandalised - under "Notable econometricians" the 1989 Nobel Laureate Trygve Haavelmo has been erased in favour of an entry for a fictional Lloyd Jones. No such person was awarded a Nobel Prize in any year. The tip-off is the reference to the "Sun Shagger Of The Year" award. The false information was added in the anonymous edit on May 17 2010. NeilGarratt (talk) 20:26, 29 May 2010 (UTC)

## History and criticism

I think the article might benefit from a section on the history of econometrics and perhaps some mention, as raised by some above, of some criticism of econometrics, and the defense against such criticisms. This I think should include a mention of the Keynes-Tinbergen debate which I might start a little stub on. But would history and criticism be better - less contentious in a separate article? Perhaps adding to the little - methodology of econometrics article? These Morgan, MS (1991) The history of econometric ideas Cambridge University Press, Louçã, Francisco (2007) The years of high econometrics: a short history of the generation that reinvented economics, Routledge and http://sims.princeton.edu/yftp/Tinbergen/TinbergenTalkSlides.pdf might be indicative of the kind of thing that might be a useful source (Msrasnw (talk) 11:10, 27 November 2011 (UTC))

Well, I think most readers of this page would appreciate that someone is brave enough to suggest a willingness to undertake the above ("wise" is a related term here that comes to mind ; ). Whether the effort is a lot or a little, my guess is that the value of marginal product is likely to be large for the foreseeable future. History and (including, but not only, as) criticism sounds promising, interesting, and consistent with working criticism into the narrative per WP:STRUCTURE. The best critics may be those who move the subject forward (or provide stimulus for others doing so, possibly including Keynes -- no slouch he when it came to the probability part).
As suggested above, criticism may be distinguished from debunking. Google scholar citations are one gauge of impact. Referencing in standard sources, such as those above, is another. I'm also impressed at how much history of the subject there is in M. Hashem Pesaran's superb 1987 article "Econometrics," The New Palgrave: A Dictionary of Economics, reprinted in J. Eatwell et al., eds. (1990). Econometrics: The New Palgrave, pp. 1-34, & 2008 revision by J. Geweke, J. Horowitz, and H. P. Pesaran per outline as well. On methodology, there is of course Kevin Hoover’s magisterial review in the Palgrave Handbook. So, there's an abundance of good sources to choose from. Whatever use is made of the methodology article here will be insufficient for that subject in itself, which I'd hope would flourish. If enough of the text or substance of the latter is incorporated in Econometrics (which I'd hope), I'd favor recognizing on this page the methodology Edit history here, an acknowledgement of its contribution here for its larger viewing audience. Most knowledgeable persons I think would appreciate what an improvement such incorporation could make. I hope that there would be no reluctance to use the relevant links at Economic methodology#Scope per: * issues critical to the practice and progress of econometrics" footnote [9] there, if they fit, either for "Econometrics" or "Methodology of econometrics". --Thomasmeeks (talk) 19:26, 29 November 2011 (UTC)

## Criticism section

I removed the criticism section. Most of the criticisms are out of context. Leamer is an econometrician himself. Coase is cited as an unpublished quotation and who knows the context(s). He is likely only taking about bad practices, which isn't a criticism of econometrics itself. Every econometrics course teaches you how to avoid spurious correlation. Lucas and Solow are criticizing specific types of models. Every econometric model has been criticized. This criticism is part of econometrics. Only the Austrian and Robinson mentions are possibly relevant, but I don't think these are really worth saving as they were.

If you're not saying they're definitely not relevant, them I'm putting them back in. Byelf2007 (talk) 7 March 2012
Correction--the Robinson thing ain't a criticism. I'll make the Austrian critique bit better (just putting stuff from "Austrian School" article in basically). Byelf2007 (talk) 7 March 2012
Medicine does not contain a section on criticism by phrenologists or psychic surgeons. Statistics does not contain criticism from Hard Times. There is not need to list criticism by "the Austrian school" or Joan Robinson, and such BS wastes the public's time. 09:51, 12 April 2012 (UTC)
I wrote the text of the removed "criticism" section and I'll freely admit it was far from perfect (but before it was a one liner... ). Criticisms of the (mis)use of econometric methods by econometricians are hugely relevant to the scope of the article, though I've taken the hint and reworded to make the scope of their criticisms more clear. I've balanced that reinclusion by removing the WP:Undue Weight on the Austrian School's preferred deductive method and their WP:Fringe claim that observable statistical regularities in human behaviour don't exist: that's been moved in the the helpfully-created Criticisms of econometrics article. Perhaps "Limitations" would be a better section title although "criticism" seems to be a Wikipedia norm...Dtellett (talk) 08:18, 14 April 2012 (UTC)

I have started a new article on Criticisms of econometrics in order to keep some of the stuff which I think is useful available. I think it would be preferable here - but to avoid conflict a seperate article might be less contentious. (Msrasnw (talk) 11:06, 12 April 2012 (UTC)) PS: Medicine does seem to have a controversy section and Statistics a section on the misuse of statistics and I think some link to Dicken's critique of utilitarianism might be useful in the misuse statistics section but perhaps on the missuse of statistics page might be better. (Msrasnw (talk) 11:35, 12 April 2012 (UTC))

I'm removing the "Lucas critique" section. It's misleading to imply that this is a general criticism of econometrics. The Lucas critique was a criticism of a specific class of econometric models used in macroeconomics. These models have been supplanted (or supplemented) by newer models since the 1970s. I don't see a reason to include an old criticism of a specific type of model in this section. Plenty of econometric models have been criticized over the years.--Bkwillwm (talk) 23:07, 24 April 2012 (UTC)
As far as I know, there is currently no mainstream criticism of econometrics, as a whole. Sure, I too have read in the internet some people criticizing studies that employ applied econometrics which they label "pointless gymnastics"; however, none of them seem to understand econometrics. Valid criticism can only come from a top notched econometrician or a statistician specialized in multivariate regression. This criterion excludes Hayek and most, if not all, austrian school economists. Having said that, let me address the Leamer critique. It is not a critique of econometrics per se, but a critique of the often undisclosed specification searches made by econometricians. It should belong in a Wikipedia entry of Model Specification in Econometrics, not in the main "Econometrics" entry. By including these criticisms, the editors seem to be pushing their own Point of View (POV). Mainstream economists do not criticize the "use of mathematical and statistical methods in economic data", that is, econometrics, as an entire branch of Economics. If McCloskey thinks that most economists over the last years have misused the interpretation of statistical techniques, that will eventually made its way in journals as original research and it will lead to better practices. Nonetheless, I doubt it will ever make anyone drop the use of econometrics, in any of its forms, from economics. On one hand, I ask fellow editors to please revert the edits and eliminate the criticism section from this entry. On the other hand I agree that this entry should maintain a conservative tone regarding the effectiveness of econometrics for producing economic inferences, like causal relationships. A balanced entry should strip the article of any sort of "magic" qualities of econometrics. --Forich (talk) 15:30, 6 July 2012 (UTC)

Please see WP:NOT and WP:EL; c.f., WP:EW.

Thanks! 09:48, 12 April 2012 (UTC)

## Criticism section: Austrian critiques

I think there could be some mention of Austrian economist objections to econometrics here. I am not sure should we need "Herbener" to be mentioned though. Perhaps a compromise would be just to have something like: The Austrian School of economics argues that econometrics has no predictive value due to the tendency of human behavior to change. Anythoughts? (Msrasnw (talk) 11:34, 16 April 2012 (UTC))

Wikipedia does not promote fringe views and pseudoscience. This insanity can go onto a blog.... 13:25, 16 April 2012 (UTC)
I am not sure how to engage with this line of argument. At least one possibly respectable/acceptable econometrics methodology book (Keuzenkamp, H. A. (2000). Probability, econometrics and truth: The methodology of econometrics. Cambridge, UK: Cambridge University Press. (Reviewed in Journal of the American Statistical Association, Journal of Economic Literature, Journal of Economic History)) has a whole section on Austrian economists' views. The section is on Section 5.2 The Austrian critique on prediction and scientism. The book overall is pushing a subjective interpretation of probability and the associated approach of Bayesian inference and calls for a returng to the positivist tradition, Karl Pearson! He is not aguing for Austrian approach in general. Best wishes (Msrasnw (talk) 13:53, 16 April 2012 (UTC))
There are intelligent, coherent discussions of inherent limits to prediction of human behavior by e.g. Karl Popper, Herb Simon, Jon Elster, Alasdair MacIntyre (interpreting Quine on the complexity of propositions about others' intentions), etc. These are reliable, high quality sources, which cannot be said for the typical "Austrian" enthusiast, alas. Oskar Morgenstern was an Austrian scientist and philosopher who wrote many interesting comments about the difficulties of prediction. Despite his affection for the Menger family, he probably had contempt for the obscurantism of many so-called Austrian economists. Perhaps Wald made comments?
Cambridge UP published a nice monograph on statistical games, discussing weirdnesses of econometricians predicting housing prices for the Olympic games, when such forecasts (in Sydney) were influencing construction, etc.
However, such discussion deals with social sciences (including non-human intelligent agents) rather than econometrics per se, don't you think? Maybe you could write an article on such limitations to prediction, which could be summarized her (per WP:Summary style). 14:47, 16 April 2012 (UTC)

Kiefer.Wolfowitz, you are removing criticism from the Austrian School and Hayek by claiming it's fringe, but you have not explained how it's fringe. -- Vision Thing -- 22:06, 22 April 2012 (UTC)

Existing criticism is sourced to the world's best economists. Leamer is one of the world's best econometricians and has been for decades, and is especially notable because he's original. Lucas won the Nobel Prize and has been Chair at Chicago.
It is better to use highest quality and most reliable sources for articles. You admit that your proposed addition may meet the standard of WP:RS but is of much lower quality than the article's existing sources, I assume.
We don't engage in original research here, I don't have to explain why it's fringe or why 1+1=2. I suggest that we ask for second opinions at WikiProject Economics.
If you edit war again, you may be blocked. The policy clearly states that the burden is on you, who want to add new material to gain consensus on the talk page. You waited less than a minute from leaving a complaint, not an argument, here before you restored the contentious material. (Please understand that this notice will be regarded as the equivalent of a final notice before blocking by an administrator; I don't template your talk page out of courtesy, per WP:Don't template the regulars.) 09:52, 23 April 2012 (UTC)
Comment - It seems to me fine to have some mention of Austrian criticism of the use of econometrics here. I am not really sure of the problem and it seems to me unfair to remove the couple of sourced lines that Vision Thing wishes to add. Austrian views don't seem to me to qualify as fringe being one the main alternative approaches. (Msrasnw (talk) 09:59, 23 April 2012 (UTC))
Kiefer.Wolfowitz, two editors support inclusion while you are only one who objects. Hayek was one of the world's best economists who also received Nobel Prize. Moreover, his article that is mentioned, The Use of Knowledge in Society, was recently selected by The American Economic Review as one of the top 20 articles in its history. So your claims about "fringe view" and "pseudoscience" are completely groundless. -- Vision Thing -- 10:08, 23 April 2012 (UTC)
Robert Solow has named Austrian economics among the "fringes" of economics in his review of The New Palgrave.
Would you respond to my discussion of the criticisms incoherently plastered on this article before? I tried to suggest intelligent discussions of the substantive issues.
Wait a few days for the notice at the WikiProject economics to bring more views. The record shows that this Austrian junk was pushed onto the page first, and then sources were found to support the POV push.
Perhaps, thinking rationally and being aware of "public choice" economics, AER added Hayek's article to attract donations from right-wing foundations? ;p
Is there anything in Hayek that hasn't been better said by Marschak, Hurwicz, Simon, Arrow, etc.? 10:34, 23 April 2012 (UTC)
I think even if we don't like the Austrian approach Hayek is notable and in his Nobel Memorial Prize in Economic Sciences lecture (Friedrich August von Hayek The Pretence of Knowledge The American Economic Review , Vol. 79, No. 6, Nobel Lectures and 1989 Survey of Members (Dec., 1989), pp. 3-7) he is critical of the econometric approach arguing that the illusion, however, that we can use this technique for the determination and prediction of the numerical values of those magnitudes; and this has led to a vain search for quantitative or numerical constants. I think an economics' Nobel laureate talking about this in his speech published in a national economic society's key journal (The American Economic Review) should be enough. (Msrasnw (talk) 11:28, 23 April 2012 (UTC))
A PS: I have just looked up the Solow quote from the NYT (and see we can now access some articles for free) and one thing I think is important to note is that he lists the dissenting fringes within academic economics. That is, in Solow's view, in academic economics. I think that is not the same as pseudo science or fringe science which might be outside their academic disciplines by most definitions. (Msrasnw (talk) 12:08, 23 April 2012 (UTC))
You agree then Solow calls it a "fringe". Do you agree that no source calls it mainstream economics? 13:54, 23 April 2012 (UTC)
Yes Solow does list it as part of the fringe within academic economics. Is Solow right and if so we allowed to include things that Solow says are in the fringe within academic economics? As for your second point I think, I think we can find sources indicating that Austrian economics has been refered to as being within the mainstream. Roger Backhouse, a mainstream UK historian of economic thought, has documented how In the 1930s Hayek was part of the mainstream. (Backhouse (2000) Austrian Economics and the Mainstream: View from the Boundary - QJAE) and There are, for example, those who think of Austrian economics as a branch of mainstream neoclassical economics Boettke (1994). The Elgar companion to Austrian economics. Atkinson and John's (2001) Studying Economics argue - Mainstream economics can be roughly divided between three groups which for simplicity we can call neo-classical (or supply-side) Keynesian ... and Austrian. This last point does not seem so important to the question at hand as I think we can include criticisms of the mainstream from outside the mainstream as well as from within. (Msrasnw (talk) 15:17, 23 April 2012 (UTC))
I agree, there is no reason to keep Hayek's criticism out, and according to your quote claim that Austrian economics is pseudoscience is completely bogus. -- Vision Thing -- 11:58, 24 April 2012 (UTC)
I disagree with KW's claim that Austrian economics is pseudoscience. Being on the "fringe" of the academic world isn't the same as doing "fringe" science. However, Austrians are a marginalized group in academia, and definitely not part of the mainstream (even Austrians will tell you that). Austrian views should be given little, if any, weight in this article. I wouldn't oppose any mention of Austrian economics, but I think the current content isn't worth inclusion. In the current text, it's not clear what Hayek's alternative is. Looking at the second source, he seems to be pushing "vernacular" analysis, which isn't notable enough for inclusion here. It's also not clear that what his criticism of "aggregation" covers (based on the source, it extends to all statistical analysis of the economy). We'd have to go a lot more into Hayek's criticism to make sense, but I don't think it's notable enough to warrant all that coverage. --Bkwillwm (talk) 22:58, 24 April 2012 (UTC)
On the subtly made points by B & M, B's cite of Hayek's Nobel lecture may be unique in his actually citing "econometrics" (in passing as to William Petty, the "founder" of econometrics William Petty (!), w the implicature that econ hasn't made much progress since Isaac Newton & Petty's time. So a nice jibe, possibly worth repeating, esp. w M's quotation above if it's in a narrative that voices parallel concerns expressed by great econometricians or or other theorists like Sims, Leamer, Koopmans, et al. There are plenty of Google scholar hits of [ Hayek "econometrics"],[1], at least one of which is actually on econometrics[2].
A nice source of lively quotations on econometrics is The Elgar Dictionary of Economic Quotations, referenced in its index. In Economic methodology#History and generalizations, there is an example of how to showcase quotations on a different econ subject. --Thomasmeeks (talk) 17:10, 26 April 2012 (UTC)
I agree with  Kiefer. This criticism section smells like POV pushing to me. Lets fix that. --Forich (talk) 15:38, 6 July 2012 (UTC)

## Keynes's criticisms

Do you think the criticism section might usefully have some mention of Keynes's methodological problems with Tinbergen's econometrics? I think these were more considered/important than the Austrian ones or would this be better in another article? (00:26, 25 April 2012 (UTC))

I don't we should mention Keynes here. His criticisms are outdated. Many advances have been made in econometrics over the past few decades. Criticisms from older "greats" don't retain their relevance when the subject matter has changed so much. I think the problem with including Keynes's criticism, and the idea of a criticism section generally, is that most "criticisms" (spurious correlations, identification issues, bad data, etc) are known issues and econometricians spend a great deal of time developing techniques to address them. This article should explain the techniques used to avoid potential estimation problems instead of lumping them together in a "criticism" section. I think the only criticisms possibly worth mentioning are those (like McCloskey's and Leamer's) that document current and prevalent mistakes made in econometrics. Both Keynes's and Hayek's criticisms belong in a history of econometrics article. New Palgrave's article on "Econometrics" has an extensive history of the discipline. I'd like to get that going eventually, but I only contribute sporadically.--Bkwillwm (talk) 05:11, 25 April 2012 (UTC)
Reply. I think some brief mention of the Austrian criticsims and Keynes might be nice - because I think they are still view by some as being still relevant. The Austrians still reject the whole econometrics approach. Keynes seems to me to be a mix of both a worry about the methodological foundation of the whole process and about the practice. Supporting refs might on Keynes's criticisms more directly might include these. Hendry, D.F. (1980). Econometrics - Alchemy or Science ?, Economica, 47, August who argues that Keynes's criticisms "make an excellent list of what might be called problems of the linear regression model" and Pesaran, H. and Smith, R. (1985). ‘Keynes on Econometrics’, in Lawson, T and Pesaran, H. (eds) (1985). Keynes’ Economics: Methodological Issues thought Keynes was "despite his technical confusion" right technically and logically (p. 147). Also Keuzenkamp, H. A. (2000). Probability, Econometrics and Truth. The methodology of econometrics, Cambridge: Cambridge University Press. argues that in the light of much current practice a sceptical attitude like Keynes' criticisms are still justified.
But yes I think you are right about the need for a history of econometrics article and perhaps these thing should go there but I do think it useful to have a criticism/limitations section here including both notable criticisms coming from those that reject the approach outright and those that have criticised the practice rather than the approach per se. But perhaps these should be limited here and lead elsewhere for more discussion. (Msrasnw (talk) 10:59, 25 April 2012 (UTC))
The measured but vigorous discussion & quality refs. above are heartening.
My comment in the preceding section (Talk:Econometrics#Criticism section: Austrian critiques) I think applies here too as to earlier historical concerns livening up the narrative or providing an agreeable segue to discussion of contemporary practice.* No reason either to let the absence of a History of econometrics article delay putting up good stuff in the article. Worse comes to worse, this article could spin off historical aspects to a future history article. But that day may be far off. The New Palgrave article on econometrics (w links from fn. 1 of Econometrics:Pesaran (1987). "Econometrics," The New Palgrave: A Dictionary of Economics, v. 2, p. 8 [pp. 8-22]. Reprinted in J. Eatwell et al., eds. (1990). Econometrics: The New Palgrave, pp. 1-34. Abstract (2008) revision) shows one way to work history in.
* For the benefit of other readers, the 1939 review article by Keynes, excerpted here, is referred to in The New Palgrave article. --Thomasmeeks (talk) 18:23, 26 April 2012 (UTC)
I'm not completely opposed to including the Keynes/Tinbergen debate in a history section. My main concern is that we don't create a criticism section that creates a false sense of controversy about econometrics. Many of the authors mentioned by Msrasnw above are notable econometricians, and while criticize some econometric work, they aren't opposed to econometrics generally. It seems like our criticism section here tends to be worded as if debates within econometrics are actually arguments against econometrics.--Bkwillwm (talk) 04:01, 30 April 2012 (UTC)