Hostname: page-component-7479d7b7d-qlrfm Total loading time: 0 Render date: 2024-07-11T11:10:50.907Z Has data issue: false hasContentIssue false
  • English
  • Français

Reconciling Conflicting Gauss-Markov Conditions in the Classical Linear Regression Model

Published online by Cambridge University Press:  04 January 2017

Roger Larocca
Roger Larocca*
Affiliation:
Department of Political Science, Purdue University, West Lafayette, IN 47907. e-mail: larocca@purdue.edu
Get access Rights & Permissions [Opens in a new window]

Abstract

This article reconciles conflicting accounts of Gauss-Markov conditions, which specify when ordinary least squares (OLS) estimators are also best linear unbiased (BLU) estimators. We show that exogeneity constraints that are commonly assumed in econometric treatments of the Gauss-Markov theorem are unnecessary for OLS estimates of the classical linear regression model to be BLU. We also generalize a set of necessary and sufficient conditions first established by McElroy (1967, Journal of the American Statistical Association 62:1302–1304), but not yet generally recognized in the econometric literature, that are appropriate for many political science applications. McElroy's conditions relax the traditional Gauss-Markov restriction on autocorrelation in the errors to allow a type of correlation, exchangeability, that has two desirable characteristics: (1) exchangeable data occur in a potentially important class of political science models, and (2) the form of autocorrelation that occurs in exchangeable data has a ready intuition. We thus show that a common class of sample selection models that does not satisfy the Gauss-Markov conditions specified in econometrics textbooks is, in fact, BLU under OLS estimation.

Type
Research Article
Information
Political Analysis , Volume 13 , Issue 2 , Spring 2005 , pp. 188 - 207
Copyright
Copyright © The Author 2005. Published by Oxford University Press on behalf of the Society for Political Methodology 

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Achen, C. H. 1982. Interpreting and Using Regression. Sage.Google Scholar
Aitken, A. C. 1935. “On Least Squares and Combination of Observations.” Proceedings of the Royal Society of Edinburgh, Sec. A. 55: 42–48.Google Scholar
Anderson, T. W. 1948. “On the Theory of Testing Serial Correlation.” Skandinavisk Aktuarietidskrift 31: 88–116.Google Scholar
Arnold, S. F. 1979. “Linear Models with Exchangeably Distributed Errors.” Journal of the American Statistical Association 74(365): 194–199.Google Scholar
Baksalary, J. K., and Van Eijnsbergen, A. C. 1988. “A Comparison of Two Criteria for Ordinary-Least-Squares Estimators to be Best Linear Unbiased Estimators.” American Statistician 42(3): 205–208.Google Scholar
Balestra, P. 1970. “On the Efficiency of Ordinary Least-Squares in Regression Models.” Journal of the American Statistical Association 65(331): 1330–1337.Google Scholar
Balestra, P., and Nerlove, M. 1966. “Pooling Cross Section and Time Series Data in the Estimation of a Dynamic Model: The Demand for Natural Gas.” Journal of the American Statistical Association 65(331): 1330–1337.CrossRefGoogle Scholar
Beck, N., and Katz, J. N. 1995. “What To Do (and Not To Do) with Time-Series Cross Section Data.” The American Political Science Review 89(3): 634–647.Google Scholar
Berry, W. D. 1993. Understanding Regression Assumptions. Newbury Park, CA: Sage.Google Scholar
Berry, W. D., and Sanders, M. S. 2000. Understanding Multivariate Research. Boulder: Westview.Google Scholar
Breen, R. 1996. Regression Models: Censored, Sample Selected, or Truncated Data. Newbury Park: Sage.Google Scholar
Bryant, P. 1984. “Geometry, Statistics, Probability: Variations on a Common Theme.” American Statistician 38(1): 38–48.Google Scholar
Chernoff, H., and Teichner, H. 1958. “A Central Limit Theorem for Sums of Interchangeable Random Variables.” Annals of Mathematical Statistics 29(1): 118–130.Google Scholar
Davidson, R., and MacKinnon, J. G. 1993. Estimation and Inference in Econometrics. New York: Oxford University Press.Google Scholar
Davidson, R., and MacKinnon, J. G. 2004. Econometric Theory and Methods. New York: Oxford University Press.Google Scholar
De Finetti, B. 1937. “Foresight: Its Logical Laws, Its Subjective Sources.” Reprinted in Studies in Subjective Probability, eds. Kyburg, H. E. and Smokler, H. E. New York: Wiley.Google Scholar
DeGroot, M. H., and Schervish, M. J. 2002. Probability and Statistics. 3rd ed. Boston: Addison-Wesley.Google Scholar
Dougherty, C. 2002. Introduction to Econometrics. 2nd ed. New York: Oxford University Press.Google Scholar
Draper, D., Hodges, J. S., Mallows, C. L., and Pregibon, D. 1993. “Exchangeability and Data Analysis.” Journal of the Royal Statistical Society A 156(1): 9–37.Google Scholar
Farebrother, R. W. 1985. “McElroy's Condition.” Letter to the editor. American Statistician 39(3): 240.Google Scholar
Graybill, F. A. 1976. Theory and Application of the Linear Model. North Scituate, MA: Duxbury.Google Scholar
Greene, W. H. 2000. Econometric Analysis. 4th ed. Upper Saddle River, NJ: Prentice Hall.Google Scholar
Gujarati, D. 1995. Basic Econometrics. 3rd ed. McGraw-Hill.Google Scholar
Halmos, Paul. 1991. “The Theory of Unbiased Estimation.” Annals of Mathematical Statistics. 17(1): 34–43.Google Scholar
Halperin, H. 1951. “Normal Regression Theory in the Presence of Intra-Class Correlation.” Annals of Mathematical Statistics. 22(4): 573–580.Google Scholar
Hamilton, J. D. 1994. Time Series Analysis. Princeton, NJ: Princeton University Press.Google Scholar
Hanushek, E., and Jackson, J. 1977. Statistical Methods for Social Scientists. New York: Academic.Google Scholar
Harville, D. A. 1981. “Unbiased and Minimum Unbiased Estimation of Estimable Functions for Fixed Linear Models with Arbitrary Covariance Structure.” Annals of Statistics. 9(3): 633–637.Google Scholar
Hayashi, F. 2000. Econometrics. Princeton: Princeton University Press.Google Scholar
Heckman, J. J. 1976. “The Common Structure of Statistical Models of Truncation, Sample Selection and Limited Dependent Variables and a Simple Estimator for Such Models.” Annals of Economic and Social Measurement 5: 475–92.Google Scholar
Henderson, R. 1932. “A Postulate for Observations.” Annals of Mathematical Statistics 3: 32–37.Google Scholar
Johnston, J., and DiNardo, J. 1997. Econometric Methods. 4th ed. New York: McGraw-Hill.Google Scholar
Judge, G., Griffiths, W. E., Hill, R. C., Lutkepohl, H., and Lee, T-C. 1985. The Theory and Practice of Econometrics. New York: John Wiley and Sons.Google Scholar
Kempthorne, O. 1989. “Comment on Puntanen and Styan.” American Statistician 43(3): 161–162.Google Scholar
Kennedy, P. 1998. A Guide to Econometrics. 4th ed. Cambridge, MA: MIT Press.Google Scholar
Kmenta, J. 1986. Elements of Econometrics. Ann Arbor, MI: University of Michigan Press.Google Scholar
Koford, K. 1990. “Dimensions in Congressional Voting.” American Political Science Review 93: 949–962.Google Scholar
Kotz, S., Balakrishnan, N., and Johnson, N. L. 2000. Continuous Multivariate Distributions, Volume 1: Models and Applications. 2nd ed. New York: John Wiley.Google Scholar
Kruskal, W. 1968. “When Are Gauss-Markov and Least Squares Estimators Identical? A Coordinate-Free Approach.” Annals of Mathematical Statistics 39(1): 70–75.Google Scholar
Kullbak, S., and Yasaimaibodi, Y. 1967. “A Property of Symmetric (Interchangeable) Random Variables.” American Statistician. 32–33.Google Scholar
Lindley, D. V., and Novick, Melvin R. 1981. “The Role of Exchangeability in Inference.” Annals of Statistics 9(1): 45–58s.Google Scholar
Maddala, G. S. 1977. Econometrics. New York: McGraw-Hill.Google Scholar
Maddala, G. S. 1983. Limited Dependent and Qualitative Variables in Econometrics. New York: Cambridge University Press.Google Scholar
Magness, T. A., and McGuire, J. B. 1983. “Comparison of Least Squares and Minimum Variance Estimates of Regression Parameters.” Annals of Mathematical Statistics 33(2): 462–470.Google Scholar
Markov, A. 1900. The Calculus of Probabilities. Moscow (in Russian).Google Scholar
Mathew, T. 1983. “Linear Estimation with an Incorrect Dispersion Matrix in Linear Models with a Common Linear Part.” Journal of the American Statistical Association 78(382): 468–471.Google Scholar
Mathew, T. 1986. “McElroy's Condition: Comments on Milliken and Albohali and Farebrother.” Letter to the editor. American Statistician 40(2): 179.Google Scholar
McCarty, N., and Groseclose, T. 2001. “The Politics of Blame: Bargaining Before an Audience.” American Journal of Political Science 45(1).Google Scholar
McElroy, F. W. 1967. “A Necessary and Sufficient Condition that Ordinary Least-Squares Estimators be Best Linear Unbiased Estimators.” Journal of the American Statistical Association 62: 1302–1304.Google Scholar
McElroy, F. W. 1976. “Optimality of Least Squares in Models with Unknown Error Covariance Matrix.” Journal of the American Statistical Association 71(354): 374–377.Google Scholar
Milliken, G., and Albohali, M. 1984. “On Necessary and Sufficient Conditions for Ordinary Least Squares Estimators to be Best Linear Unbiased Estimators.” American Statistician. 38(4): 298–299.Google Scholar
Nelson, F. D. 1984. “Efficiency of the Two-Step Estimator for Models with Endogenous Sample Selection.” Journal of Econometrics 24: 181–196.Google Scholar
Newey, W. K., and West, K. D. 1987. “A Simple, Positive Semi-Definite, Heteroskedasticity and Autocorrelation Consistent Covariance Matrix.” Econometrica 55: 703–708.Google Scholar
Oleszek, W. J. 2001. Congressional Procedures and the Policy Process. Washington, DC: CQ Press.Google Scholar
Puntanen, S. 1986. “Further Comment on Milliken and Albohali.” Letter to the editor. American Statistician 40(2): 179.Google Scholar
Puntanen, S., and Styan, G. P. H. 1989. “The Equality of the Ordinary Least Squares Estimator and the Best Linear Unbiased Estimator.” American Statistician 43(3): 153–161.Google Scholar
Rosenthal, H. 1992. “The Unidimensional Congress is Not the Result of Selective Gatekeeping.” American Journal of Political Science 36(1): 31–35.Google Scholar
Ruud, P. A. 2000. An Introduction to Classical Econometric Theory. New York: Oxford University Press.Google Scholar
Searle, Shayle. 1982. Matrix Algebra Useful for Statistics. New York: John Wiley and Sons.Google Scholar
Schneider, J. E. 1979. Ideological Coalitions in Congress. Westport, CT: Greenwood.Google Scholar
Smith, S. S. 1989. Call to Order: Floor Politics in the House and Senate. Washington, DC: Brookings.Google Scholar
Snyder, J. M. 1992. “Committee Power, Structure-Induced Equilibria, and Roll Call Votes.” American Journal of Political Science 36(1): 1–30.Google Scholar
Spanos, A. 1999. Probability Theory and Statistical Inference: Econometric Modeling with Observational Data. Cambridge: Cambridge University Press.Google Scholar
Stock, J. H., and Watson, M. W. 2003. Introduction to Econometrics. Boston: Addison Wesley.Google Scholar
Theil, H. 1971. Principles of Econometrics. New York: John Wiley and Sons.Google Scholar
Van Doren, P. M. 1990. “Can We Learn the Causes of Congressional Decisions from Roll Call Data?” Legislative Studies Quarterly 15: 311–340.Google Scholar
Verbeek, M. 2000. Modern Econometrics. New York: John Wiley and Sons.Google Scholar
Watson, G. S. 1967. “Linear Least Squares Regression.” Annals of Mathematical Statistics 38(6): 1679–1699.CrossRefGoogle Scholar
White, H. 1980. “A Heteroskedasticity-Consistent Covariance Matrix Estimator and a Direct Test for Heteroskedasticity.” Econometrica 48: 817–838.Google Scholar
Wiorkowski, J. J. 1975. “Unbalanced Regression Analysis with Residuals Having a Covariance Structure of Intra-Class Form.” Biometrika 31: 611–618.Google Scholar
Wooldridge, J. 2002. Econometric Analysis of Cross Section and Panel Data. Cambridge, MA: MIT Press.Google Scholar
Wooldridge, J. 2003. Introductory Econometrics: A Modern Approach. Mason, OH: Thomson/Southwestern.Google Scholar
Zyskind, George. 1962. “On Conditions for Equality of Best and Simple Linear Least Squares Estimators.” Abstract. Annals of Mathematical Statistics 33: 1502–1503.Google Scholar
Zyskind, George. 1967. “On Canonical Forms, Non-negative Covariance Matrices and Best and Simple Least Squares Linear Estimators in Linear Models.” Annals of Mathematical Statistics 38(4): 1092–1109.Google Scholar
Zyskind, George. 1969. “Parametric Augmentation and Error Structures under which Certain Simple Least Squares and Analysis of Variance Procedures Are Also Best.” Journal of the American Statistical Association 64: 1353–1368.Google Scholar