|
There have been many criticisms of econometrics' usefulness as a discipline and perceived widespread methodological shortcomings in econometric modelling practices. At one level these criticisms are based on the fact that economic structure and behaviour is subject to change and accurately observed relationships in the past may not continue into the future. As Robert Lucas famously observed this is particularly true where economic policy changes are implemented based on econometric models that fail to account for the possibility of patterns changing ''as a deliberate response to the policy.'' The heterodox Austrian School of economics entirely rejects the validity of econometrics as a method of predicting human behaviour, preferring to use the deductive method. Some, but by no means all Post Keynesian economists dislike the use of econometric methods, perhaps influenced by Keynes' own aversion to "arid mathematical formalism" in economics.〔Gerrard, Bill (2002) "The role of econometrics in a radical methodology publisher" in: Sheila C. Dow; John Hillard (Ed.) (''Post Keynesian Econometrics,Microeconomics and the Theory of the Firm'' ), Edward Elgar. ISBN 1858985846 p.113〕 Joan Robinson was offered the role of vice president of the Econometric Society but declined on the basis she wouldn't want to be part of the editorial committee of a journal she "could not read".〔("In praise of … Joan Robinson" ) The Guardian, Friday 9 July 2010〕 == Difficulties in model specification == Like other forms of statistical analysis, badly specified econometric models may show a spurious correlation where two variables are correlated but causally unrelated. Economist Ronald Coase is widely reported to have said "if you torture the data long enough it will confess".〔Gordon Tullock, "A Comment on Daniel Klein's 'A Plea to Economists Who Favor Liberty'", ''Eastern Economic Journal'', Spring 2001, note 2 (Text: "As Ronald Coase says, 'if you torture the data long enough it will confess'." Note: "I have heard him say this several times. So far as I know he has never published it.")〕 McCloskey argues that in published econometric work, economists tend to rely excessively on statistical techniques and often fail to use economic reasoning for including or excluding variables.〔 〕 Economic variables are not readily isolated for experimental testing, but Edward Leamer argues that there is no essential difference between econometric analysis and randomized trials or controlled trials provided judicious use of statistical techniques eliminates the effects of collinearity between the variables. Economists are often faced with a high number of often highly collinear potential explanatory variables, leaving researcher bias to play an important role in their selection. Leamer argues that economists can mitigate this by running statistical tests with different specified models and discarding any inferences which prove to be "fragile", concluding that "professionals ... properly withhold belief until an inference can be shown to be adequately insensitive to the choice of assumptions". 抄文引用元・出典: フリー百科事典『 ウィキペディア（Wikipedia）』 ■ウィキペディアで「Criticisms of econometrics」の詳細全文を読む スポンサード リンク
|