A comparative study of algorithms for solving seemingly unrelated regressions models

The computational efficiency of various algorithms for solving seemingly unrelated regressions (SUR) models is investigated. Some of the algorithms adapt known methods; others are new. The first transforms the SUR model to an ordinary linear model and uses the QR decomposition to solve it. Three others employ the generalized QR decomposition to solve the SUR model formulated as a generalized linear least-squares problem. Strategies to exploit the structure of the matrices involved are developed. The algorithms are reconsidered for solving the SUR model after it has been transformed to one of smaller dimensions.

[1]  E. Kontoghiorghes,et al.  Computing 3SLS Solutions of Simultaneous Equation Models with a Possible Singular Variance–Convariance Matrix , 1997 .

[2]  C. Paige,et al.  A Constrained Least Squares Approach to the General Gauss-Markov Linear Model , 1981 .

[3]  V. K. Srivastava,et al.  Estimation of seemingly unrelated regression equations: A brief survey , 1979 .

[4]  P. Dhrymes.  Topics in Advanced Econometrics , 1989 .

[5]  William M. Bolstad,et al.  An estimation method for the seemingly unrelated regression model with contemporaneous covariances based on an efficient recursive algorithm , 1987 .

[6]  Elias Dinenis,et al.  Solving Triangular Seemingly Unrelated Regression Equations Models on Massively Parallel Systems , 1996 .

[7]  Inge Söderkvist.  On algorithms for generalized least squares problems with ill-conditioned covariance matrices , 1996 .

[8]  Erricos John Kontoghiorghes,et al.  Parallel Strategies for Computing the Orthogonal Factorizations Used in the Estimation of Econometric Models , 1999, Algorithmica.

[9]  A. Zellner.  An Efficient Method of Estimating Seemingly Unrelated Regressions and Tests for Aggregation Bias , 1962 .

[10]  E. Kontoghiorghes,et al.  Estimating seemingly unrelated regression models with vector autoregressive disturbances , 2003 .

[11]  Ed Anderson,et al.  LAPACK Users' Guide , 1995 .

[12]  Phoebus J. Dhrymes.  Linear and nonlinear simultaneous equations , 1994 .

[13]  C. Paige.  Computer solution and perturbation analysis of generalized linear least squares problems , 1979 .

[14]  Eva Ferreira,et al.  An algorithm to estimate time-varying parameter SURE models under different types of restriction , 2003, Comput. Stat. Data Anal..

[15]  H. Theil,et al.  Three-Stage Least Squares: Simultaneous Estimation of Simultaneous Equations , 1962 .

[16]  J. Chavas.  Recursive estimation of simultaneous equation models , 1982 .

[17]  C. Lawson,et al.  Solving least squares problems , 1976, Classics in applied mathematics.

[18]  C. C. aige.  Numerically stable computations for general univariate linear models , 1978 .

[19]  Gene H. Golub,et al.  Matrix computations , 1983 .

[20]  Sanjit K. Mitra,et al.  Kronecker Products, Unitary Matrices and Signal Processing Applications , 1989, SIAM Rev..

[21]  A. Zellner.  Estimators for Seemingly Unrelated Regression Equations: Some Exact Finite Sample Results , 1963 .

[22]  Erricos John Kontoghiorghes,et al.  Parallel Algorithms for Linear Models: Numerical Methods and Estimation Problems , 2000 .

[23]  J. H. Wilkinson,et al.  Reliable Numerical Computation. , 1992 .

[24]  L. Telser,et al.  Iterative Estimation of a Set of Linear Regression Equations , 1964 .

[25]  A. Koutsoyiannis.  Three-stage Least Squares , 1977 .

[26]  Charles L. Lawson,et al.  Solving least squares problems , 1976, Classics in applied mathematics.

[27]  Inconsistencies in SURE Models: Computational Aspects , 2000 .

[28]  Erricos John Kontoghiorghes,et al.  An alternative approach for the numerical solution of seemingly unrelated regression equations models , 1995 .

[29]  E. Kontoghiorghes,et al.  Estimation of VAR Models Computational Aspects , 2003 .

[30]  C. C.,et al.  FAST NUMERICALLY STABLE COMPUTATIONS FOR GENERALIZED LINEAR LEAST SQUARES PROBLEMS * , .

[31]  Erricos John Kontoghiorghes.  Computational methods for modifying seemingly unrelated regressions models , 2004 .

[32]  Erricos John Kontoghiorghes.  Parallel Strategies for Solving SURE Models with Variance Inequalities and Positivity of Correlations Constraints , 2000 .

[33]  Erricos John Kontoghiorghes,et al.  Seemingly unrelated regression model with unequal size observations: computational aspects , 2002, Comput. Stat. Data Anal..

[34]  Åke Björck,et al.  Numerical methods for least square problems , 1996 .

[35]  David A. Belsley.  Paring 3SLS calculations down to manageable proportions , 1992 .