Iatrogenic Specification Error: A Cautionary Tale of Cleaning Data
It is common in empirical research to use what appear to be sensible rules of thumb for cleaning data. Measurement error is often the justification for removing (trimming) or recoding (winsorizing) observations whose values lie outside a specified range. This paper considers identification in a linear model when the dependent variable is mismeasured. The results examine the common practice of trimming and winsorizing to address the identification failure. In contrast to the physical and laboratory sciences, measurement error in social science data is likely to be more complex than simply additive white noise. We consider a general measurement error process which nests many processes including the additive white noise process and a contaminated sampling process. Analytic results are only tractable under strong distributional assumptions, but demonstrate that winsorizing and trimming are only solutions for a particular class of measurement error processes. Indeed, trimming and winsorizing may induce or exacerbate bias. We term this source of bias Iatrogenic' (or econometrician induced) error. The identification results for the general error process highlight other approaches which are more robust to distributional assumptions. Monte Carlo simulations demonstrate the fragility of trimming and winsorizing as solutions to measurement error in the dependent variable.
|Date of creation:||Mar 2003|
|Date of revision:|
|Publication status:||published as Bollinger, Christopher R. and Amitabh Chandra. "Iatrogenic Specification Error: A Cautionary Tale Of Cleaning Data," Journal of Labor Economics, 2005, v23(2,Apr), 235-257.|
|Contact details of provider:|| Postal: National Bureau of Economic Research, 1050 Massachusetts Avenue Cambridge, MA 02138, U.S.A.|
Web page: http://www.nber.org
More information through EDIRC
Please report citation or reference errors to , or , if you are the registered author of the cited work, log in to your RePEc Author Service profile, click on "citations" and make appropriate adjustments.:
- Bollinger, Christopher R., 1996. "Bounding mean regressions when a binary regressor is mismeasured," Journal of Econometrics, Elsevier, vol. 73(2), pages 387-399, August.
- David Card & Alan B. Krueger, 1992.
"School Quality and Black-White Relative Earnings: A Direct Assessment,"
The Quarterly Journal of Economics,
Oxford University Press, vol. 107(1), pages 151-200.
- David Card & Alan B. Krueger, 1991. "School Quality and Black-White Relative Earnings: A Direct Assessment," NBER Working Papers 3713, National Bureau of Economic Research, Inc.
- Joshua Angrist & Alan Krueger, 1998.
"Empirical Strategies in Labor Economics,"
98-7, Massachusetts Institute of Technology (MIT), Department of Economics.
- Juhn, Chinhui & Murphy, Kevin M & Pierce, Brooks, 1993. "Wage Inequality and the Rise in Returns to Skill," Journal of Political Economy, University of Chicago Press, vol. 101(3), pages 410-42, June.
- Horowitz, Joel L & Manski, Charles F, 1995. "Identification and Robustness with Contaminated and Corrupted Data," Econometrica, Econometric Society, vol. 63(2), pages 281-302, March.
- Manski, C.F., 1992. "Identification Problems in the Social Sciences," Working papers 9217, Wisconsin Madison - Social Systems.
- John Bound & Alan B. Krueger, 1989.
"The Extent of Measurement Error In Longitudinal Earnings Data: Do Two Wrongs Make A Right?,"
NBER Working Papers
2885, National Bureau of Economic Research, Inc.
- Bound, John & Krueger, Alan B, 1991. "The Extent of Measurement Error in Longitudinal Earnings Data: Do Two Wrongs Make a Right?," Journal of Labor Economics, University of Chicago Press, vol. 9(1), pages 1-24, January.
- MacDonald, Glenn M & Robinson, Chris, 1985. "Cautionary Tails about Arbitrary Deletion of Observations; or, Throwing the Variance Out with the Bathwater," Journal of Labor Economics, University of Chicago Press, vol. 3(2), pages 124-52, April.
- Barry T. Hirsch & Edward J. Schumacher, 2004.
"Match Bias in Wage Gap Estimates Due to Earnings Imputation,"
Journal of Labor Economics,
University of Chicago Press, vol. 22(3), pages 689-722, July.
- Hirsch, Barry & Schumacher, Edward J., 2003. "Match Bias in Wage Gap Estimates Due to Earnings Imputation," IZA Discussion Papers 783, Institute for the Study of Labor (IZA).
- Goldberger, Arthur S., 1981. "Linear regression after selection," Journal of Econometrics, Elsevier, vol. 15(3), pages 357-366, April.
- Bound, John, et al, 1994. "Evidence on the Validity of Cross-Sectional and Longitudinal Labor Market Data," Journal of Labor Economics, University of Chicago Press, vol. 12(3), pages 345-68, July.
- Dean R. Hyslop & Guido W. Imbens, 2000.
"Bias from Classical and Other Forms of Measurement Error,"
NBER Technical Working Papers
0257, National Bureau of Economic Research, Inc.
- Hyslop, Dean R & Imbens, Guido W, 2001. "Bias from Classical and Other Forms of Measurement Error," Journal of Business & Economic Statistics, American Statistical Association, vol. 19(4), pages 475-81, October.
- Mellow, Wesley & Sider, Hal, 1983. "Accuracy of Response in Labor Market Surveys: Evidence and Implications," Journal of Labor Economics, University of Chicago Press, vol. 1(4), pages 331-44, October.
- Bollinger, Christopher R, 1998. "Measurement Error in the Current Population Survey: A Nonparametric Look," Journal of Labor Economics, University of Chicago Press, vol. 16(3), pages 576-94, July.
- Marco Manacorda, 2004. "Can the Scala Mobile Explain the Fall and Rise of Earnings Inequality in Italy? A Semiparametric Analysis, 19771993," Journal of Labor Economics, University of Chicago Press, vol. 22(3), pages 585-614, July.
When requesting a correction, please mention this item's handle: RePEc:nbr:nberte:0289. See general information about how to correct material in RePEc.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: ()
If references are entirely missing, you can add them using this form.