Forecasting with Econometric Methods Folklore versus Fact

Forecasting with Econometric Methods Folklore versus Fact -...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
Electronic copy available at: http://ssrn.com/abstract=664063 Published in Journal of Business, 51 (4), 1978, 549-564 Forecasting with Econometric Methods: Folklore versus Fact J. Scott Armstrong The Wharton School, University of Pennsylvania Abstract Evidence from social psychology suggests that econometricians will avoid evidence that disconfirms their beliefs. Two beliefs of econometricians were examined: (1) Econometric methods provide more accurate short-term forecasts than do other methods; and (2) more complex econometric methods yield more accurate forecasts. A survey of 21 experts in econometrics found that 95% agreed with the first statement and 72%0 agreed with the second. A review of the published empirical evidence yielded little sup- port for either of the two statements in the 41 studies. The method of multiple hypotheses was suggested as a research strategy that will lead to more effective use of disconfirming evidence. Although this strategy was suggested in 1890, it has only recently been used by econometricians. Introduction This paper is concerned with the use of econometric methods for forecasting in the social sciences. Although this is not the only use of econometric methods, it is one of the ways they are used; it is also the use that can most easily be validated. The paper examines only the predictive validity of econometric models. The impor- tance of predictive validity has long been recognized by econometricians. Christ (1951) stated, "The ultimate test of an econometric model . . . comes with checking its predictions." "Econometric methods" are defined in this paper as quantitative approaches that attempt to use causal relationships in forecasting. In particular, they refer to models based on regression analysis. This definition conforms to common usage of the term "econometric methods." "Folklore" is used here to reflect what econometricians believe, as judged by what they do. "Fact" is based upon published empirical studies. The first part of this paper draws upon evidence from social psychology to explain why folklore persists. Most of the evidence is based upon the behavior of people in general. However, there is evidence to suggest that scientists act as other people when testing their favored hypotheses. Two examples of the discrepancy between folklore and fact are provided in the second part of the paper. These are only two of a number of possible examples, but they deal with two important questions. First, do econometric methods provide the most accurate way to obtain short-range forecasts? Second, do complex econometric methods provide more accurate forecasts than simple econometric methods? The third part of the paper describes the method of multiple hypotheses. This method should help to overcome folklore. The Persistence of Folklore
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Image of page 2
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

Page1 / 12

Forecasting with Econometric Methods Folklore versus Fact -...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online