Abstract
A seemingly unrelated regression model has been commonly used for describing a set of different regression models with correlations. This paper discusses the estimation of the covariance matrix in a seemingly unrelated regression model under Stein’s loss function. In particular, when the correlation matrix is assumed to be known, a best equivariant estimator of the covariance matrix is derived. Its properties are investigated and a connection to a best equivariant estimator of regression coefficients given in a previous study is shown. Results of numerical simulations and an illustrative example are also presented to compare the best equivariant estimator of the covariance matrix with several conventional covariance matrix estimators.
Similar content being viewed by others
References
Ando T, Zellner A (2010) Hierarchical Bayesian analysis of the seemingly unrelated regression and simultaneous equation models using a combination of direct Monte Carlo and importance sampling techniques. Bayesian Anal 5(1):65–96
Breusch TS, Pagan AR (1980) The Lagrange multiplier test and its application to model specification in econometrics. Rev Econ Stud 47(1):239–253
Costa N, Lourenço J, Pereira ZL (2012) Responses modeling and optimization criteria impact on the optimization of multiple quality characteristics. Comput Ind Eng 62(4):927–935
Derringer G, Suich R (1980) Simultaneous optimization of several response variables. J Qual Technol 12(4):214–219
Horn RA, Johnson CR (1994) Topics in matrix analysis. Cambridge University Press, Cambridge
Galimberti G, Scardovi E, Soffritti G (2016) Using mixtures in seemingly unrelated linear regression models with non-normal errors. Stat Comput 26(5):1025–1038
Hadjiantoni S, Kontoghiorghes EJ (2017) Estimating large-scale general linear and seemingly unrelated regressions models after deleting observations. Stat Comput 27(2):349–361
Hejazi TH, Esfahani MS, Mahootchi M (2015) Optimization of degree of conformance in multiresponse-multistage systems with a simulation-based metaheuristic. Qual Reliab Eng Int 31(4):645–658
Henderson DJ, Kumbhakar SC, Li Q, Parmeter CF (2015) Smooth coefficient estimation of a seemingly unrelated regression. J Econom 189(1):148–162
Kariya T (1981a) Bounds for the covariance matrices of Zellner’s estimator in the SUR model and the 2SAE in a heteroscedastic model. J Am Stat Assoc 76(376):975–979
Kariya T (1981b) Tests for the independence between two seemingly unrelated regression equations. Ann Stat 9(2):381–390
Kurata H (1999) On the efficiencies of several generalized least squares estimators in a seemingly unrelated regression model and a heteroscedastic model. J Multivar Anal 70(1):86–94
Kurata H (2004) One-sided tests for independence of seemingly unrelated regression equations. J Multivar Anal 90(2):393–406
Kurata H, Kariya T (1996) Least upper bound for the covariance matrix of a generalized least squares estimator in regression with applications to a seemingly unrelated regression model and a heteroscedastic model. Ann Stat 24(4):1547–1559
Kurata H, Matsuura S (2016) Best equivariant estimator of regression coefficients in a seemingly unrelated regression model with known correlation matrix. Ann Inst Stat Math 68(4):705–723
Liu A (2002) Efficient estimation of two seemingly unrelated regression equations. J Multivar Anal 82(2):445–456
Ma T, Ye R (2010) Efficient improved estimation of the parameters in two seemingly unrelated regression models. J Stat Plan Inference 140(9):2749–2754
Ng VM (2002) Robust Bayesian inference for seemingly unrelated regressions with elliptical errors. J Multivar Anal 83(2):409–414
Percy DF (1992) Predictions for seemingly unrelated regressions. J R Stat Soc: Ser B 54:243–252
Peterson JJ, Quesada GM, Castillo ED (2009) A Bayesian reliability approach to multiple response optimization with seemingly unrelated regression models. Qual Technol Quant Manag 6(4):353–369
Riani M (2004) Robust multivariate transformations to normality: constructed variables and likelihood ratio tests. Stat Methods Appl 13(2):179–196
Riggs KR, Young PD, Young DM (2016) Confidence ellipsoids for the primary regression coefficients in two seemingly unrelated regression models. Stat Methodol 32:1–13
Shah HK, Montgomery DC, Carlyle WM (2004) Response surface modeling and optimization in multiresponse experiments using seemingly unrelated regressions. Qual Eng 16(3):387–397
Soumaya M, Gaffke N, Schwabe R (2015) Optimal design for multivariate observations in seemingly unrelated linear models. J Multivar Anal 142:48–56
Srivastava VK, Giles DEA (1987) Seemingly unrelated regression equations models. Dekker, New York
Zellner A (1962) An efficient method of estimating seemingly unrelated regressions and tests for aggregation bias. J Am Stat Assoc 57(298):348–368
Zellner A (1963) Estimators for seemingly unrelated regression equations: some exact finite sample results. J Am Stat Assoc 58(304):977–992
Zellner A, Ando T (2010) A direct Monte Carlo approach for Bayesian analysis of the seemingly unrelated regression model. J Econom 159(1):33–45
Zhang L, Ma Y, Ouyang L, Liu J (2016) Balancing the subjective and objective weights for correlated multiresponse optimization. Qual Reliab Eng Int 32(3):817–835
Zhao L, Xu X (2017) Generalized canonical correlation variables improved estimation in high dimensional seemingly unrelated regression models. Stat Probab Lett 126:119–126
Acknowledgements
We would like to thank anonymous reviewers for constructive and helpful comments. This work was supported by JSPS KAKENHI Grant Number 15K15952.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Matsuura, S., Kurata, H. Covariance matrix estimation in a seemingly unrelated regression model under Stein’s loss. Stat Methods Appl 29, 79–99 (2020). https://doi.org/10.1007/s10260-019-00473-x
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10260-019-00473-x