Dasgupta, Madhuchhanda and Mishra, SK
(2004):
*Least absolute deviation estimation of linear econometric models: A literature review.*

Preview |
PDF
MPRA_paper_1781.pdf Download (214kB) | Preview |

## Abstract

Econometricians generally take for granted that the error terms in the econometric models are generated by distributions having a finite variance. However, since the time of Pareto the existence of error distributions with infinite variance is known. Works of many econometricians, namely, Meyer & Glauber (1964), Fama (1965) and Mandlebroth (1967), on economic data series like prices in financial and commodity markets confirm that infinite variance distributions exist abundantly. The distribution of firms by size, behaviour of speculative prices and various other recent economic phenomena also display similar trends. Further, econometricians generally assume that the disturbance term, which is an influence of innumerably many factors not accounted for in the model, approaches normality according to the Central Limit Theorem. But Bartels (1977) is of the opinion that there are limit theorems, which are just likely to be relevant when considering the sum of number of components in a regression disturbance that leads to non-normal stable distribution characterized by infinite variance. Thus, the possibility of the error term following a non-normal distribution exists.

The Least Squares method of estimation of parameters of linear (regression) models performs well provided that the residuals (disturbances or errors) are well behaved (preferably normally or near-normally distributed and not infested with large size outliers) and follow Gauss-Markov assumptions. However, models with the disturbances that are prominently non-normally distributed and contain sizeable outliers fail estimation by the Least Squares method. An intensive research has established that in such cases estimation by the Least Absolute Deviation (LAD) method performs well.

This paper is an attempt to survey the literature on LAD estimation of single as well as multi-equation linear econometric models.

Item Type: | MPRA Paper |
---|---|

Institution: | North-Eastern Hill University, Shillong |

Original Title: | Least absolute deviation estimation of linear econometric models: A literature review |

Language: | English |

Keywords: | Lad estimator; Least absolute deviation estimation; econometric model; LAD Estimator; Minimum Absolute Deviation; Robust; Outliers; L1 Estimator; Review of literature |

Subjects: | C - Mathematical and Quantitative Methods > C4 - Econometric and Statistical Methods: Special Topics > C46 - Specific Distributions ; Specific Statistics C - Mathematical and Quantitative Methods > C3 - Multiple or Simultaneous Equation Models ; Multiple Variables > C30 - General C - Mathematical and Quantitative Methods > C3 - Multiple or Simultaneous Equation Models ; Multiple Variables |

Item ID: | 1781 |

Depositing User: | Sudhanshu Kumar Mishra |

Date Deposited: | 13 Feb 2007 |

Last Modified: | 26 Sep 2019 10:07 |

References: | · Abdelmalek, N N (1974). On the Discrete Linear L1 Approximation and L1 Solution of Over- determined Linear Equations, Journal of Approximation Theory, Vol. 11, pp. 35 – 53. · Amemiya, T (1982). The Two-Stage Least Absolute Deviation Estimators, Econometrica, Vol. 50 (1-3), pp. 689-711. · Ashar, V C & T D Wallace (1963). A Sampling Study of Minimum Absolute Deviation Estimators, Operations Research, Vol. 11, pp. 747-758. · Barrodale, I (1968). L1 Approximation and the Analysis of Data, Applied. Statistics, Vol. 17, pp. 51-57. · Barrodale, I. & F D K Roberts (1973). An Improved Algorithm for Discrete L1 · Approximation, SIAM. Journal of Numerical Analysis, Vol.. 10, pp. 839-848. · Basmann, R L (1975). A Generalized Classical Method of Linear Estimation of Coefficients in a Structural Equation, Econometrica, Vol. 25, pp. 77-84. · Basset, G Jr. & R. Koenkar (1978). Asymptotic Theory of Least Absolute Error Regression, Journal of American Statistical Association, Vol. 73, pp. 618-622. · Blattberg, R & T Sargent (1971). Regression with Non-Gaussian Stable Disturbances: Some Sampling Results, Econometrica, Vol. 39, pp. 501 – 510. · Charnes, A & C E Lemke (1954). Computational Theory of Linear Programming: The Bounded Variables Problem, Graduate School of Industrial. Administration, Carnegie Inst. of Technol., Pittsburg, Pennsylvania. 20 · Charnes, A, W W Cooper & R O Ferguson (1955). Optimal Estimation of Executive Compensation by Linear Programming, Management Science, Vol. 1, pp. 138-151. · Chen, X (1996). On a Problem of Strong Consistency of Least Absolute Deviation Estimates. Statistical Sinica, Vol. 6, pp. 481-489. · Cragg, J (1967). On The Relative Small-Sample Properties of Several Structural Equation Estimators, Econometrica, Vol. 35, pp. 89 – 110. · Dasgupta, M (1992). Degree of Over-Identification and its Effects on the Performance of Estimators. M Phil. Dissertation, Department of Economics, NEHU, Shillong (unpub). · Edgeworth, F Y (1887). On Discordant Observations, Philosophical Magazine, Vol. 5(24), pp. 364 - 375. · Edgeworth, F Y (1888). On a New Method of Reducing Observations Relating to Several Quantities”, Philosophical Magazine, Vol. 5 (25), pp. 185 – 191. · Edgeworth, F Y (1923). On the Use of Medians for Reducing Observations Relating to Several Quantities , Philosophical Magazine, 6th Series. Pp. 1074 – 1088. · Fair, R C ( 1974). On Robust Estimation of Econometric Models, Annals of Economic and Social Measurement, Vol. 3,pp. 667 – 678. · Fair, R C (1994). Estimating and Testing the US Model, Yale Univ. · Fama, E F (1965). The Behaviour of Stock Market Prices, Journal of Business, Vol. 38, pp. 34 – 105. · Fisher, W D (1961). A Note on Curve Fitting with Minimum Deviation by Linear Programming”, Journal of American Statistical Association, Vol. 56, pp. 359 – 361. · Froberg, C E (1964). Introduction to Numerical Analysis. Addison- Wesley Publishing Co. Inc. London. · Gillett, B E (1979). Introduction to Operations Research. Tata McGraw Hill, New Delhi. · Glahe, F R & J G Hunt (1970). The Small Sample Properties of Simultaneous Equation Least Absolute Estimators vis-a-vis Least Squares Estimators, Econometrica, Vol. 5(38), pp. 742– 53. · Haavelmo, T (1943). The Statistical Implications of a System of Simultaneous Equations, Econometrica, Vol. 11, pp. 1–12. · Haavelmo, T (1947). Methods of Measuring the Marginal Propensity to Consume. Journal of American Statistical Association, Vol. 42, pp. 105-22. · Hammersley, J M & D C Handcomb (1964). Monte Carlo Methods, John Wiley, New York. Hill, R W & W P Holland (1977). Two Robust Alternatives to Least SquaresRegression, Journal of the American Statistical Association, Vol. 72, pp. 828-833. · Hitomi, K & M Kagihara (2001). Calculation Method for Non-Linear Dynamic Least Absolute Deviation Estimator. J. of Japan Statist. Society, Vol. 31(1), pp. 39-51. · Hood, W C & T C Koopmans (Ed.) (1953). Studies in Econometric Method, Cowels Foundation Monograph 14, John Wiley, New York. · Huber, P J (1964). Robust Estimation of a Location Parameter, Annals of Mathematical Statistics, 35 (73 – 101). · Intriligator, M D (1978). Econometric Models, Techniques and Applications, Prentice Hall, Englewood Cliffs, New Jersey. · Johnston, J (1963). Econometric Methods, McGraw-Hill, New York. · Judge, G G, W E Griffiths, R C Hill & T Lee (1980). The Theory and Practice of Econometrics. John Wiley, New York. · Kapur, J N & H C Saxena (1982). Mathematical Statistics. S Chand & Co. New Delhi. · Khazzoom, J D (1976). An Indirect Least Squares Estimator for Over identified Equations, Econometrica, Vol. 44 (4) , pp. 741–750. · Kim, T H & C Muller (2000). Two-Stage Quantile Regression, Discussion Paper in Economics #00/1, Nottingham University, January. · Knuth, D E (1969). The Art of Computer Programming. Addison Wesley. · Koopmans, T C, H Rubin & R B Leipnik (1950). Measuring the Equation Systems of Dynamic Economics. in T. C. Koopmans (ed.) (1950) Statistical Inference in Dynamic Economic Models, Wiley, New York, pp. 53 – 237. · Krishnamurthy, E V & S K Sen (1976). Computer-Based Numerical Algorithms. Affiliated East-West Press, New Delhi. · Kuester, J L & J H Mize (1973). Optimization Techniques with Fortran. McGraw-Hill Book Company, New York. · Mandlebroth, B B (1967). The Variation of Certain Speculative Prices, Journal of Business, Vol. 36, pp. 394 – 419. · Medhi, N (1992). A Study on the Behaviour of the Minimum Absolute Deviation (MAD) Regression Estimator, M. Phil. Dissertation. Dept. of Economics, NEHU., Shillong (unpub). · Metropolis, N & S Ulam (1949). The Monte Carlo method, Journal of the American Statistical Association, Vol. 44 (247), pp. 335-341. · Meyer, J R & R R Glauber (1964). Investment Decisions : Economic Forecasting and Public Policy, Harvard Business School Press, Cambridge, Massachusetts. · Mishra. S K (1997). Generalisation of Indirect Least Squares to Estimation of Over-identified Equations of a Multi-Equation Linear Econometric Model, Assam Statistical Review, Vol. 9(1), pp. 57 – 66. · Nagar, A L (1960). A Monte Carlo Study of Alternative Simultaneous Equation Estimators, Econometrica, Vol. 28, pp. 573 – 590. · National Bureau of Standard (1951). Monte Carlo Method. Applied Math Serial 12, Washington. · Naylor, T H (Ed.) (1969). The Design of Computer Simulation Experiments. Duke Univ. Press, Durham, N. C. · Newey, W K (1985). Semi-Parametric Estimation of Limited Dependent Variables Models with Endogenous Explanatory Variables. Annales de’l INSEE, Vol. 59-60, pp. 219-235. · Nyquist, H & A Westlund (1977). L1Versus L2 Norm Estimation in Interdependent Systems when Residual Distributions are Stable, Mimeo, Dept. of Statistics, Univ. of Umea. · Oveson, R M (1969). Regression Parameter Estimation by Minimizing the Sum of Absolute Errors, Doctoral Dissertation, Harvard University, Cambridge, Massachusetts (unpub). · Pagan, A R (1986). Two-Stage and Related Estimators and their Applications. Review of Economic Studies, Vol. 57, pp. 517-538. · Phillips P C B (1991). A Shortcut to LAD Estimator Asymptotics. Econometric Theory, Vol. 7(4), pp. 450-463. · Pollard, D (1991). Asymptotics for Least Absolute Deviation Regression Estimators. Econometric Theory, Vol. 7(2), pp. 186-199. · Portnoy S & R Koenker (1997). The Gaussian Hare and the Laplacian Tortise: Computability of Squared-error versus Absolute-error Estimators. Statistical Science, Vol. 12, pp. 279-300. · Powell, J L (1984). Least Absolute Deviations Estimation for the Censored Regression Model. J. of Econometrics, Vol. 25, pp. 303-325. · Rhodes, E C (1930). Reducing Observations by the Method of Minimum Deviations, Phil. Magazine 7th Series. Pp. 974 – 992. · Rao, C R & S K Mitra (1971). Generalised Inverse of Matrices and its Applications. John Wiley, New York. · Rao, S S (1978). Optimization: Theory and Applications. Wiley Eastern Limited, New Delhi. · Rice, J R & J S White (1964). Norms for Smoothing and Estimation, SIAM Review, Vol. 6, pp. 243 – 256. · Robers, P D. & A Ben-Israel (1969). An Interval Programming Algorithm for Discrete Linear L1 Approximation Problems, Journal of Approximation Theory, Vol. 2, pp. 323 – 336. · Schlossmacher, E J (1973). An Alternative Technique for Absolute Deviations Curve Fitting, Journal of the American Statistical Association, Vol. 68, pp. 857 – 859. · Simmonard, M (1966). Linear Programming, Prentice Hall, Englewood Cliffs, New Jersey. · Singh. L K (1993). Performance of Generalised Indirect Least Squares in Over-Identified Equation Estimation: A Monte Carlo Experiment, M Phil. Dissertation, Department of Economics, NEHU, Shillong (unpub). · Singleton, R R (1940). A Method for Minimizing the Sum of Absolute Errors, Am. Math. Statist. Vol. 11, pp. 301 – 310. · Smith, V K (1973). Monte Carlo Methods, Lexington Books, Lexington. · Smith, V K & T W Hall (1972). A Comparison of Maximum Likelihood versus BLUE Estimators, The Review of Economics and Statistics, Vol. 54, pp. 186 – 190. · Spyropoulous, K, E Kiountouzis & A Young (1973). Discrete Approximation in the L1 Norm, Computer Journal, Vol. 16, pp. 180 – 186. · Texas Instruments Inc (1979). TI Programmable 58C/59 Master Library, Texas Instruments Inc. Texas. · Theil H (1953). Repeated Least Squares Applied to Complete Equation Systems, Central Planning Bureau (Mimeo), The Hague. · Theil, H (1957). Specification Errors and the Estimation of Economic Relationships, Review of International Statistical Institute, Vol. 25, pp. 41- 51. · Theil, H (1961). Economic Forecasts and Policy, North Holland Publishing Co., Amsterdam. · Theil, H (1962). Three Stage Least Squares: Simultaneous Estimation of Simultaneous Equations, Econometrica, Vol. 30, pp. 54 – 78. · Theil, H (1971). Principles of Econometrics, John Wiley and Sons, Inc. New York. · Thomas, R L (1985). Introductory Econometrics Theory and Application, Longman Group Limited. New York. · Tylor, L D (1974). Estimation by Minimizing the Sum of Absolute Errors, in Zerembka, P (ed.), Frontiers of Econometrics, Academic Press, New York. · Usow, K H (1967). On L1 Approximation for Discrete Functions and Discretization Effects, SIAM Journal of Numerical Analysis, Vol. 44, pp. 233 –244. · Wagner, H M (1958). A Monte Carlo Study of Estimates of Simultaneous Linear Structural Equations, Econometrica, Vol. 26, pp. 117 – 133. · Wagner, H M (1959). Linear Programming Techniques for Regression Analysis, Journal of American Statistical Association, Vol. 56, pp. 206 –212. · Weiss, A A (1991). Estimating Non-linear Dynamic Models using Least Absolute Error Estimation. Econometric Theory, Vol. 7, pp. 46-68. |

URI: | https://mpra.ub.uni-muenchen.de/id/eprint/1781 |