Advanced search
Publication Cover
American Journal of Mathematical and Management Sciences Volume 4, 1984 - Issue 1-2: Statistics and Optimization: The Interface
Submit an article Journal homepage
27
Views
9
CrossRef citations to date
0
Altmetric
Original Articles

Computational Algorithms for Calculating Least Absolute Value and Chebyshev Estimates for Multiple Regression

Terry E. DielmanM. J. Neeley School of Business Texas Christian UniversityFort Worth, Texas76129
&
Roger C. PfaffenbergerM. J. Neeley School of Business Texas Christian UniversityFort Worth, Texas76129
Pages 169-197 | Published online: 14 Aug 2013

  • AbdelmalekN. N. (1975a). An efficient method for the discrete linear Li approximation problem. Mathematics of Computation, 29, 844–850.
  • AbdelmalekN. N. (1975b). Chebyshev solution of overdetermined system of linear equations. BIT, 15, 117–129.
  • AbdelmalekN. N. (1976). A computer program for the Chebyshev solution of overdetermined system of linear equations. International Journal for Numerical Methods in Engineering, 10, 1197–1202.
  • AbdelmalekN. N. (1980a). L1 solution of overdetermined systems of linear equations. ACM Transactions on Mathematical Software, 6, 220–227.
  • AbdelmalekN. N. (1980b). Algorithm 551: A FORTRAN subroutine for the L1 solution of overdetermined systems of linear equations. ACM Transactions on Mathematical Software, 6, 228–230.
  • ArmstrongR. D. and FromeE. L. (1977). A special purpose linear programming algorithm for obtaining least absolute value estimators in a linear model with dummy variables. Communications in Statistics - Simulation and Computation, B6, 383–398.
  • ArmstrongR. D. and FromeE. L. (1979). Least-absolute-value estimators for one-way and two-way tables. Naval Research Logistics Quarterly, 26, 79–96.
  • ArmstrongR. D., FromeE. L. and KungD. S. (1979). A revised simplex algorithm for the absolute deviation curve fitting problem. Communications in Statistics - Simulation and Computation, B8, 175–190.
  • ArmstrongR. D. and HultzJ. W. (1977). An algorithm for a restricted discrete approximation problem in the L1 norm. SIAM Journal on Numerical Analysis, 14, 555–565.
  • ArmstrongR. D. and KungD. S.(1978). Algorithm AS132: Least absolute value estimates for a simple linear regression problem. Applied Statistics, 27, 363–366.
  • ArmstrongR. D. and KungD. S. (1979). Algorithm AS135: Minmax estimates for a linear multiple regression problem. Applied Statistics, 28, 93–100.
  • ArmstrongR. D. and KungD. S. (1980). A dual method for discrete Chebyshev curve fitting. Mathematical Programming, 19, 186–199.
  • ArmstrongR. D. and KungM. T. (1980). An algorithm for a least absolute value regression problem with bounds on the parameters. Applied Mathematics and Computation, 7, 267–279.
  • ArmstrongR. D. and KungM. T. (1982). An algorithm to select the best subset for a least absolute value regression problem. TIMS Studies in the Management Sciences, 19, ZanaklsS. H. and RustaglJ. S., eds., Amsterdam: North-Holland Publishing Co., 67–80.
  • ArmstrongR. D. and SklarM. G. (1979). A dual method for discrete Chebychev curve fitting with linear restrictions on the parameters. American Statistical Association Statistical Computing Section Proceedings, Washington, B.C., 293–296.
  • BarrodaleI. and PhillipsC. (1975). Algorithm 495: Solution of an over-determined system of linear equations in the Chebychev norm. ACM Transactions on Mathematical Software, 1, 264–270.
  • BarrodaleI. and RobertsF. D. K. (1973). An Improved algorithm for discrete linear L1 approximation. SIAM Journal on Numerical Analysis, 10, 839–848.
  • BarrodaleI. and RobertsF. D. K. (1974). Algorithm 478: Solution of an overdetermined system of equations in the norm. Communications of the ACM, 17, 319–320.
  • BarrodaleI. and RobertsF. D. K. (1978). An efficient algorithm for discrete linear approximation with linear constraints. SIAM Journal on Numerical Analysis, 15, 603–611.
  • BarrodaleI. and YoungA. (1966). Algorithms for best L| and Loo linear approximations on a discrete set. Numerische Mathematlk, 8, 295–306.
  • BartelsR. H. and ConnA. R. (1980a). Linearly constrained discrete LT problems. ACM Transactions on Mathematical Software, 6, 594–608.
  • BartelsR. H. and ConnA. R. (1980b). Algorithm 563. A program for linearly constrained discrete L1 problems. ACM Transactions on Mathematical Software, 6, 609–614.
  • BartelsR. H. ConnA. R. and CharalambousC. (1978). On Cline's direct method for solving overdetermined linear systems In the Loo sense. SIAM Journal on Numerical Analysis, 15, 255–270.
  • BartelsR. H. ConnA. R. and SinclairJ. W. (1976). A FORTRAN program for solving overdetermined systems of linear equations in the Li sense. Technical Report 236, Mathematical Sciences Dept., John Hopkins University, BaltimoreMaryland.
  • BartelsR. H. ConnA. R. and SinclairJ. W. (1978). Minimization techniques for piecewise differentiable functions: The L1 solution to an overdetermined linear system. SIAM Journal on Numerical Analysis, 15, 224–241.
  • BartelsR. H. and GolubG. H. (1968a). Stable numerical methods for obtaining the Chebychev solution to an overdetermined system of equations. Communications of the ACM, 11, 401–406.
  • BartelsR. H. and GolubG. H. (1968b). Algorithm 328. Chebyshev solution to an overdetermined linear system. Communications of the ACM, 11, 428–430.
  • BassettG. and KoenkerR. (1978). Asymptotic theory of least absolute error regressions. Journal of the American Statistical Association, 73, 618–622.
  • BassettG. and KoenkerR. (1982). An empirical quantile function for linear models with lid errors. Journal of the American Statistical Association, 77, 407–415.
  • BloomfieldP. and StlegerW. (1980). Least absolute deviations curve-fitting. SIAM Journal on Scientific and Statistical Computing, 1, 290–301.
  • BoscovichR. J. (1757). Delitteraria expedltone per pontlficiam ditlonem, et synopsis amplioris operis, ac habentur plura ejus ex exemplaria etiam sensorum impressa. Bononiensi Scientiarum et Artum Institute Atque Academia Commentarii, 4, 353–396.
  • BoscovichR. J. (1760). De recentissimis graduum dimensionibus, et figura, ac magnitudine terrae inde derivanda. Philosophiae Recentioris, a Benedicto Stay in Romano Archigynasis Publico Eloquentare Professore, resibustradltae, Libri X, cum adnotianibus et Supplementis P. Rogerii Joseph Boscovich, S. J., 2, 406–426.
  • BrownleeK. A. (1965). Statistical Theory and Methodology in Science and Engineering. New York: John Wiley & Sons, Inc.
  • CharnesA., CooperW. W. and FergusonR. D. (1955). Optimal estimation of executive compensation by linear programming. Management Science, 1, 138–151.
  • ClaerboutJ. F. and MuirF. (1973). Robust modeling with erratic data. Geophysics, 38, 826–844.
  • ClineA. K. (1976). A descent method for the uniform solution to over-determined systems of linear equations. SIAM Journal on Numerical Analysis, 13, 293–309.
  • CoggerK. O. (1979). Statistical Inference in Minimum Absolute Deviation Regression. Mimeographed. LawrenceKansas: University of Kansas.
  • DanielC. and WoodF. S. (1971). Fitting Equations to Data. New York: John Wiley & Sons, Inc.
  • DavisK. R. and McKeownP. G. (1981). Quantitative Methods for Management. BostonMassachusetts: Kent Publishing Company.
  • DielmanT. E. and PfaffenbergerR. C. (1982). LAV (Least Absolute Value) estimation in linear regression: A review. TIMS Studies in the Management Sciences, 19, ZanaklsS. H. and RustagiJ. S., eds., Amsterdam: North-Holland Publishing Co., 31–52.
  • DraperN. R. and SmithH. (1966). Applied Regression Analysis. New York: John Wiley & Sons, Inc.
  • EdgeworthF. Y. (1887). On observations relating to several quantities. Hermathena, 6, 279–285.
  • EdgeworthF. Y. (1888). On a new method of reducing observations relating to several quantities. Philosophical Magazine, 25, 184–191.
  • EisenhartC. (1961). Boscovich and the combination of observations. Roger Joseph Boscovich, WhyteL. L., ed., New York: Fordham University Press, 200–212.
  • El-AttarR., VidyasagerM. and DuttaS. (1979). An algorithm for L1-norm minimization with application to nonlinear L1 approximation. SIAM Journal on Numerical Analysis, 16, 70–86.
  • ForsytheA. B. (1972). Robust estimation of straight line regression coefficients by minimizing pth power deviations. Technometrics, 14, 159–166.
  • FourierJ. B. J. (1824). Solution d'une question particuliere au calcul des inegalities, second extrait. Histoire de l'Academie des Sciences pour 1824, 47–55.
  • FromeE. L. and YakatanG. J. (1980). Statistical estimation of the pharmokinetic parameters in the one compartment open model. Communications in Statistics - Simulation and Computation, B9, 201–222.
  • GaussC. F. (1809). Theoria Motus Corporum Coelestium in Sectionibus Conlcis Solum Ambientium. Hamburg: Frid. Perthes et I. H. Besser.
  • GaussC. F. (1823). Theoria Combinationis Observatlonum Erroribus Mlnlmlm Obnoxlae. Commentationes Societatis Regiae Scientiarum Gottingensis Recentiores, 5; German summary, Gottingische Gelehrte Anzeigen (1821), 321–327 and (1823), 313–318.
  • GaussC. F. (1828). Supplementum Theoriae Combinationis Observationum Erroribus Minimis Obnoxiae. Commentationes Societatis Regine Scientiamm Gottingensis Recentiores, 6; German summary, Gottingische Gelehrte Anzeigen (1826), 1521–1527.
  • GentleJ. E., KennedyW. J. and SpositoV. A. (1977). On least absolute values estimation. Communications in Statistics - Theory and Methods, A6, 839–845.
  • GoldsteinA. A. (1956). On the method of descent in complex domains and its application to the minimal approximation of overdetermined systems of linear equations. Mathematics Pre–print No. 1, Convair Astronautics.
  • GoldsteinA. A., LevineN. and HereshoffJ. B. (1957). On the “best” and “least Q-th” approximation of an overdetermined system of linear equations. Journal of the Association for Computing Machinery, 4, 341–347.
  • HarterH. L. (1974a). The method of least squares and some alternatives - Part I. International Statistical Review, 42, 147–174.
  • HarterH. L. (1974b). The method of least squares and some alternatives - Part II. International Statistical Review, 42, 245–264.
  • HarterH. L. (1975a). The method of least squares and some alternatives - Part III. International Statistical Review, 43, 1–44.
  • HarterH. L. (1975b). The method of least squares and some alternatives - Part IV. International Statistical Review, 43, 125–190.
  • HarterH. L. (1975c). The method of least squares and some alternatives - Part V. International Statistical Review, 43, 269–278.
  • HarterH. L. (1983). The Chronological Annotated Bibliography of Order Statistics, Volume I: Pre-1950; Volume II: 1950–1959. ColumbusOhio: American Sciences Press.
  • HoffmanK. L. and ShierD. R. (1980). A test problem generator for discrete linear L1 approximation problems. ACM Transactions on Mathematical Software, 6, 587–593.
  • HoggR. V. (1974). Adaptive robust procedures: A partial review and some suggestions for future applications and theory. Journal of the American Statistical Association, 69, 909–923.
  • HoggR. V. (1979). Statistical robustness: One view of its use in applications today. The American Statistician, 33, 108–115.
  • International Mathematical and Statistical Libraries, Inc. (1980), IMSL Library 3, Reference Manual, HoustonTexas.
  • JosvangerL. A. and SpositoV. A. (1983). L1 norm estimates for the simple regression problem. Communications in Statistics - Simulation and Computation, 12, 215–221.
  • KarstO. J. (1958). Linear curve-fitting using least deviations. Journal of the American Statistical Association, 53, 118–132.
  • KelleyJ. E. (1958). An application of linear programming to curve fitting. Journal of the Society for Industrial and Applied Mathematics, 6, 15–22.
  • KennedyW. J., GentleJ. E., and SpositoV. A. (1977). A computer method for generating test problems for regression. Communications in Statistics -Simulation and Computation, B6, 21–27.
  • KlingmanD. and MoteJ. (1982). Generalized network approaches for solving least absolute value and Tchebycheff regression problems. TIMS Studies in the Management Sciences, 19, ZanakisS. H. and RustagiJ. S., eds., Amsterdam: North-Holland Publshing Co., 53–66.
  • KoenkerR. and BassettG. (1982). Tests of linear hypothesis and L1 estimation. Econometrica, 50, 1577–1583.
  • LaplaceP. S. (1786). Memoire sur la figure de la terre. Memoires de 1'Academic royale des Sciences de Paris, Annee 1783, 17–46.
  • LaplaceP. S. (1792). Sug les degres mesures des meridiens, et sur les longueurs observees sur pendule. Histoire de 1'Academic Royale des Inscriptions et Belles Lettres, aver les Memoires de litterature Tirez des Registres de cette Academie, Annee 1789, Paris.
  • LaplaceP. S. (1793). Sur quelques points du systeme du monde. Memoires de 1 Academie royal des Sciences de Paris, Annee 1789, 1–87.
  • LaplaceP. S. (1799). Traite' des Mecanique Celeste, 2, Paris: J. B. M. Deprat.
  • LaplaceP. S. (1812). Theorie Analytique des Probabllltes. Paris: Courcier.
  • LegendreA. M. (1805). Nouvelles Methodes pour la Determination des Orbites des Cometes. Paris: Courcier.
  • MathieuC. L. (1813-14). Sur les experiences du pendule, faites par les navigateurs espagnols, en differens points du globe. Connaissance des Tems, Annee 1816, 314–332.
  • MeyerJ. R. and GlauberR. R. (1964). Investment Decisions, Economic Forecasting and Public Policy. CambridgeMassachusetts: Harvard Business School Press.
  • MudrovV. I., KushkoV. L., MidhailovV. I. and OsovitskiiE. (1968). Some experiments on the use of the least-moduli method in processing orbital data. Cosmic Research, 6, 421–431.
  • MurrayW. and OvertonM. L. (1981). A projected lagrangian algorithm for nonlinear optimization. SIAM Journal on Scientific and Statistical Computing, 2, 207–224.
  • NarulaS. C. (1982). Optimization techniques in Linear Regression: A review. TIMS Studies in the Management Sciences, 19, ZanakisS. H. and RustagiJ. S., eds., Amsterdam: North Holland Publishing Co., 11–29.
  • NarulaS. C. and WellingtonJ. F. (1977a). An algorithm for the minimum sum of weighted absolute errors regression. Communications in Statistics - Simulation and Computation, B6, 341–352.
  • NarulaS. C. and WellingtonJ. F. (1977b). Subset selection using minimization of the maximum weighted absolute error. Research Report No. 37–77-P14, School of Management, Rensselaer Polytechnic Institute, TroyNew York.
  • NarulaS. C. and WellingtonJ. F. (1979). Selection of variables in linear regression using the sum of weighted absolute errors criterion. Technometrics, 21, 299–306.
  • OsborneM. R. and WatsonG. A. (1969). An algorithm for minimax approximation in the nonlinear case. The Computer Journal, 12, 63–68.
  • OsborneM. R. and WatsonG. A. (1971). On an algorithm for discrete nonlinear L1 approximation. The Computer Journal, 14, 184–188.
  • PronyR. (1804). Recherches Physico-Mathematlques sur la Theorie des Eauz. CourantesParis: L'Imprimene Imperiale.
  • RhodesE. C. (1930). Reducing observations by the method of minimum deviations. Philosophical Magazine, 9, 974–992.
  • RiceJ. R. and WhiteJ. S. (1964). Norms for smoothing and estimation. SIAM Review, 6, 243–256.
  • SadovskiA. N. (1974). L1 -norm fit of a straight line. Applied Statistics, 23, 244–248.
  • SchryerN. L. (1969). Certification of algorithm 328: Chebychev solution to an overdetermined linear system. Communications of the ACM, 12, 326.
  • ShragerR. I. and HillE. (1980). Nonlinear curve-fitting in the Li and Loo norms. Mathematics of Compulation, 34, 529–541.
  • SielkenR. L. and HartleyH. O. (1973). Two linear programming algorithms for unbiased estimation of linear models. Journal of the American Statistical Association, 68, 639–641.
  • SingletonJ. (1940). A method for minimizing the sum of absolute values of deviations. Annals of Mathematical Statistics, 11, 301–310.
  • StlefelE. (1959). Uber dlskrete and lineare Tschebyscheff-Approximationen. Numerlsche Mathematlk, 1, 1–28.
  • StlefelE. (1960). Note on Jordon elimination, linear programming and Tchebycheff approximation. Numerlsche Mathematlc, 2, 1–17.
  • TishlerA. and ZangI. (1982). An absolute deviations curve- fitting algorithm for linear models. TIMS Studies in the Management Sciences, 19, ZanakisS. H. and RustagiJ., eds., Amsterdam: North-Holland Publishing Co., 81–103.
  • UsowK. H. (1967). On L1 approximation II: Computation for discrete functions and discretization effects. SIAM Journal on Numerical Analysis, 4, 233–244.
  • WagnerH. M. (1959). Linear programming techniques for regression analysis. Journal of the American Statistical Association, 54, 206–212.
  • WatsonG. A. (1976). A method for calculating best non-linear Chebychev approximations. Journal of the Institute of Mathematical Applications, 18, 351–360.
  • WellingtonJ. F. and NarulaS. C. (1981). Variable selection in multiple linear regression using the minimum sum of weighted absolute errors criterion. Coimnunlcatlons In Statistics - Simulation and Computation, B10, 641–648.
  • WesolowskyG. O. (1981). A new descent algorithm for the least absolute value regression problem. Communications in Statistics - Simulation and Computation, B10, 479–491.
  • WilsonH. G. (1979). Upgrading transport costing methodology. Transportation Journal, 18, 49–55.
  • ZukhovitskllS. I. (1951). An algorithm for the solution of the Cebysev approximation problem in the case of a finite system of incompatible linear equations (Russian). Doklady Akademll Nauk SSSR, 79, 561–564.

Reprints and Corporate Permissions

Please note: Selecting permissions does not provide access to the full text of the article, please see our help page How do I view content?

To request a reprint or corporate permissions for this article, please click on the relevant link below:

Order Reprints Request Corporate Permissions

Academic Permissions

Please note: Selecting permissions does not provide access to the full text of the article, please see our help page How do I view content?

Obtain permissions instantly via Rightslink by clicking on the button below:

Request Academic Permissions

If you are unable to obtain permissions via Rightslink, please complete and submit this Permissions form. For more information, please visit our Permissions help page.

Supercharge Your Next Research Paper: Research and write your next paper with Jenni AI.

Related research

People also read lists articles that other readers of this article have read.

Recommended articles lists articles that we recommend and is powered by our AI driven recommendation engine.

Cited by lists all citing articles based on Crossref citations.
Articles with the Crossref icon will open in a new tab.