Abstract
The method of least squares is a statistical technique used to determine the best linear or nonlinear regression line. The method, developed independently by Legendre (1805), Gauss (1806, 1809) and Adrain (1808), has a rich and lengthy history described in an excellent six-part article by Harter (1974–6). Least squares is the technique most widely used for fitting regression lines because of its computational simplicity and because of particular optimality properties described below. Primary among these are the facts that it gives the best linear unbiased estimator (BLUE) in the case of linear regression and that it gives the maximum likelihood estimator (MLE) in the case of regression with Gaussian (normal) errors.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Bibliography
Adrain, R. 1808. Research concerning the probabilities of errors which happen in making observations. Analyst 1, 93–109.
Domowitz, I. and White, H. 1982. Misspecified models with dependent observations. Journal of Econometrics 20, 35–58.
Gallant, A.R. and White, H. 1987. A Unified Theory of Estimation and Inference for Nonlinear Dynamic Models. Oxford: Basil Blackwell.
Gauss, C.F. 1806. II Comet vom Jahr 1805. Monatliche Correspondenz zur Beförderung der Erd- und Himmelskunde 14, 181–6.
Gauss, C.F. 1809. Theoria Motus Corporum Coelestium in Sectionbus Conicis Solem Ambientium. Hamburg: F. Perthes and I.H. Besser.
Hannan, E.J. 1971. Nonlinear time-series regression. Journal of Applied Probability 8, 767–80.
Harter, H.L. 1974–6. The method of least squares and some alternatives, Parts I–VI. International Statistical Review 42, 147–74, 235–64, 282; 43, 1–44, 125–90, 269–78; 44, 113 59.
Jennrich, R. 1969. Asymptotic properties of nonlinear least squares estimators. Annals of Mathematical Statistics 40, 633–43.
Johnston, J. 1984. Econometric Methods. New York: McGraw-Hill.
Klimko, L. and Nelson, P. 1978. On conditional least squares estimation for stochastic processes. Annals of Statistics 6, 629–42.
Legendre, A.M. 1805. Nouvelles methodes pour la determination des orbites des cometes. Paris: Courcier.
Theil, H. 1971. Principles of Econometrics. New York: Wiley & Sons.
White, H. 1980a. Using least squares to approximate unknown regression functions. International Economic Review 21, 149–70.
White, H. 1980b. Nonlinear regression on cross-section data. Econometrica 48, 721–46.
White, H. 1980c. A heteroskedasticity-consistent covariance matrix estimator and a direct test for heteroskedasticity. Econometrica 48, 817–38.
White, H. 1981. Consequences and detection of misspecified nonlinear regression models. Journal of the American Statistical Association 76, 419–33.
White, H. 1984. Asymptotic Theory for Econometricians. Orlando: Academic Press.
White, H. and Domowitz, I. 1984. Nonlinear regression with dependent observations. Econometrica 52, 143–62.
Editor information
Copyright information
© 1990 Palgrave Macmillan, a division of Macmillan Publishers Limited
About this chapter
Cite this chapter
White, H. (1990). Least Squares. In: Eatwell, J., Milgate, M., Newman, P. (eds) Time Series and Statistics. The New Palgrave. Palgrave Macmillan, London. https://doi.org/10.1007/978-1-349-20865-4_15
Download citation
DOI: https://doi.org/10.1007/978-1-349-20865-4_15
Publisher Name: Palgrave Macmillan, London
Print ISBN: 978-0-333-49551-3
Online ISBN: 978-1-349-20865-4
eBook Packages: Palgrave History CollectionHistory (R0)