Abstract
Linear and nonlinear multivariate least sum of absolute deviations regression models are profiled and evaluated. A chance-corrected measure of agreement between observed and predicted values is presented, a technique for establishing empirically-derived quantile limits for predicted values is introduced, and a permutation-based inference procedure for the measure of agreement is described.
Similar content being viewed by others
References
P. Arabie, Was Euclid an unnecessarily sophisticated psychologist?, Psychometrika 56(1991)567–587.
I. Barrodale and F.D.K. Roberts, An improved algorithm for discrete ℓ1 linear approximation, SIAM J. Numer. Anal. 10(1973)839–848.
I. Barrodale and F.D.K. Roberts, Algorithm 478: Solution of an overdetermined system of equations in the ℓ1 norm, Comm. ACM 17(1974)319–320.
K.J. Berry and P.W. Mielke, A generalization of Cohen's kappa agreement measure to interval measurement and multiple raters, Educ. Psychol. Meas. 13(1988)921–933.
R. Blattberg and T. Sargent, Regression with non-Gaussian stable disturbances: Some sampling results, Econometrica 39(1971)501–510.
R.J. Boscovich, De litteraria expeditione per pontificiam ditionem, et synopsis amplioris operis, ac habentur plura ejus ex exemplaria etiam sensorum impressa, Bononiesi Scientiarum et Artum Instituto atque Academia Commentarii 4(1757)353–396.
N. Bowditch, Observations of the comet of 1807, Mem. Amer. Acad. Arts and Sci. 3(1809)1–17.
W.R. Cotton, G. Thompson and P.W. Mielke, Real-time mesoscale prediction on workstations, Bull. Amer. Meteor. Soc. 75(1994)349–362.
T.E. Dielman, Least absolute value estimation in regression models: An annotated bibliography, Commun. Statist.-Theor. Meth. 13(1984)513–541.
T.E. Dielman, A comparison of forecasts from least absolute value and least squares regression, J. Forecast. 5(1986)189–195.
T.E. Dielman, Corrections to a comparison of forecasts from least absolute value and least squares regression, J. Forecast. 8(1989)419–420.
T. Dielman and R. Pfaffenberger, Least absolute value regression: Necessary sample sizes to use normal theory inference procedures, Decision Sciences 19(1988)734–743.
T.E. Dielman and E.L. Rose, Forecasting in least absolute value regression with autocorrelated errors: A small-sample study, Int. J. Forecast. 10(1994)539–547.
C. Eisenhart, Boscovich and the combination of observations, in: Roger Joseph Boscovich, ed. L.L. Whyte, Fordham University Press, New York, 1961, pp. 200–212.
C.F. Gauss, Theoria Motus Corporum Coelestium: In Sectionibus Conicis Solem Ambientium, F. Perthes and I.H. Besser, Hamburg, 1809.
J.E. Gentle, Least absolute values estimation: An introduction, Commun. Statist.-Simula. Computa. B6(1977)313–328.
W.M. Gray, C.W. Landsea, P.W. Mielke and K.J. Berry, Predicting Atlantic seasonal hurricane activity 6–11 months in advance, Weather Forecasting 7(1992)440–455.
W.M. Gray, C.W. Landsea, P.W. Mielke and K.J. Berry, Predicting Atlantic basin seasonal tropical cyclone activity by 1 August, Weather Forecasting 8(1993)73–86.
W.M. Gray, C.W. Landsea, P.W. Mielke and K.J. Berry, Predicting Atlantic basin seasonal tropical cyclone activity by 1 June, Weather Forecasting 9(1994)103–115.
H.L. Harter, The method of least squares and some alternatives I, Int. Statist. Rev. 42(1974) 147–174.
H.L. Harter, The method of least squares and some alternatives II, Int. Statist. Rev. 42(1974) 235–264.
H.L. Harter, The method of least squares and some alternatives III, Int. Statist. Rev. 43(1975) 1–44.
H.L. Harter, The method of least squares and some alternatives IV, Int. Statist. Rev. 43(1975) 125–190; 273–278.
H.L. Harter, The method of least squares and some alternatives V, Int. Statist. Rev. 43(1975) 269–272.
H.L. Harter, The method of least squares and some alternatives VI, Int. Statist. Rev. 44(1976) 113–159.
F.P. Kelly, T.H. Vonder Haar and P.W. Mielke, Imagery randomized block analysis (IRBA) applied to the verification of cloud edge detectors, J. Atmos. Oceanic Technol. 6(1989)671–679.
P.S. Laplace, Sur quelques points du systéme du monde, Mémoires de l'Academie Royale des Sciences de Paris Année (1793) 1–87.
T.J. Lee, R.A. Pielke and P.W. Mielke, Modeling the clear-sky surface energy budget during FIFE 1987, J. Geophys. Res. 100(1995)25585–25593.
T. Mathew and K. Nordström, Least squares and least absolute deviation procedures in approximately linear models, Statist. Prob. Letters 16(1993)153–158.
P.W. Mielke, Meteorological applications of permutation techniques based on distance functions, in: Handbook of Statistics, Vol. 4, P.R. Krishnaiah and P.K. Sen, eds., North-Holland, Amsterdam, 1984, pp. 813–830.
P.W. Mielke, L 1, L 2 and L ∞ regression models: Is there a difference?, J. Stat. Plann. Inference 13 (1987)430.
P.W. Mielke, K.J. Berry, C.W. Landsea and W.M. Gray, Artificial skill and validation in meteorological forecasting, Weather Forecasting 11(1996)153–169.
S.C. Narula and J.F. Wellington, The minimum sum of absolute errors regression: A state of the art survey, Int. Statist. Rev. 50(1982)317–326.
R. Pfaffenberger and J. Dinkel, Absolute deviations curve-fitting: an alternative to least squares, in: Contributions to Survey Sampling and Applied Statistics, H.A. David, ed., Academic Press, New York, 1978, pp. 279–294.
J. Rice and J. White, Norms for smoothing and estimation, SIAM Rev. 6(1964)243–256.
B. Rosenberg and D. Carlson, A simple approximation of the sampling distribution of least absolute residuals regression estimates, Commun. Statist.-Simul. Comp. B6(1977)421–438.
P.J. Rousseeuw, Least median of squares regression, J. Amer. Statist. Assoc. 79(1984)871–880.
O.B. Sheynin, R.J. Boscovich's work on probability, Arch. Hist. Exact Sci. 9(1973)306–324.
G.F. Simmons, Introduction to Topology and Modern Analysis, McGraw-Hill, New York, 1963.
S.M. Stigler, Studies in the history of probability and statistics, XXXIII: Laplace, Fisher, and the discovery of sufficiency, Biometrika 60(1973)439–445.
L.D. Taylor, Estimation by minimizing the sum of absolute errors, in: Frontiers in Econometrics, P. Zarembka, ed., Academic Press, New York, 1974, pp. 169–190.
D.F. Tucker, P.W. Mielke and E.R. Reiter, The verification of numerical models with multivariate randomized block permutation procedures, Meteor. Atmos. Phys. 40(1989)181–188.
I.G. Watterson, Nondimensional measures of climate model performance, Int. J. Climatol. 16(1996) 379–391.
H.G. Wilson, Least squares versus minimum absolute deviations estimation in linear models, Decision Sciences 9(1978)322–335.
Rights and permissions
About this article
Cite this article
Mielke, P.W., Berry, K.J. Permutation-based multivariate regression analysis: The case for least sum of absolute deviations regression. Annals of Operations Research 74, 259–268 (1997). https://doi.org/10.1023/A:1018926522359
Issue Date:
DOI: https://doi.org/10.1023/A:1018926522359