Rank Approach for Equality Relations of BLUPs in Linear Mixed Model and its Transformed Model

Year 2021, Volume: 4 Issue: 3, 143 - 149, 30.09.2021

Melek Eriş Büyükkaya , Nesrin Güler , Melike Yiğit

https://doi.org/10.33401/fujma.889229

Abstract

A linear mixed model ($\LMM$) $\M :\yy = \mxX\BETA + \mxZ\uu + \EPS $ with general assumptions and its transformed model $\T:\mxT\yy = \mxT\mxX\BETA + \mxT\mxZ\uu + \mxT\EPS $ are considered. This work concerns the comparison problem of predictors under $\M$ and $\T$. Our aim is to establish equality relations between the best linear unbiased predictors ($\BLUP$s) of unknown vectors under two $\LMM$s $\M$ and $\T$ through their covariance matrices by using various rank formulas of block matrices and elementary matrix operations.

Keywords

BLUP , covariance matrix , linear mixed model , rank , transformed model

References

• [1] C. R. Rao, Representations of best linear unbiased estimators in the Gauss–Markoff model with a singular dispersion matrix, J. Multivariate Anal., 3 (1973), 276-292.
• [2] B. Dong, W. Guo, Y. Tian, On relations between BLUEs under two transformed linear models, J. Multivariate Anal., 131 (2014), 279-292.
• [3] Y. Tian, Matrix rank and inertia formulas in the analysis of general linear models, Open Math., 15 (1) (2017), 126-150.
• [4] G. Marsaglia, G. P. H. Styan, Equalities and inequalities for ranks of matrices, Linear Multilinear Algebra, 2 (1974), 269-292.
• [5] Y. Tian, Equalities and inequalities for inertias of Hermitian matrices with applications, Linear Algebra Appl., 433 (2010), 263-296.
• [6] B. Arendack´a, S. Puntanen, Further remarks on the connection between fixed linear model and mixed linear model, Stat. Papers, 56 (4) (2015), 1235-1247.
• [7] H. Brown, R. Prescott, Applied Mixed Models in Medicine, 2nd edn, Wiley, England, 2006.
• [8] E. Demidenko, Mixed models: Theory and applications, Wiley, New York, 2004.
• [9] D. Harville, Extension of the Gauss–Markov theorem to include the estimation of random effects, The Annals of Statistics, 4 (1976), 384-395.
• [10] S. J. Haslett, S. Puntanen, On the equality of the BLUPs under two linear mixed models, Metrika, 74 (2011), 381-395.
• [11] S. J. Haslett, S. Puntanen, A review of conditions under which BLUEs and/or BLUPs in one linear mixed model are also BLUEs and/or BLUPs in another, Calcutta Statistical Association Bulletin, 65 (1-4) (2013), 25-42.
• [12] J. Jiang, Linear and generalized linear mixed models and their applications, Springer, New York, 2007.
• [13] Y. Liu, On equality of ordinary least squares estimator, best linear unbiased estimator and best linear unbiased predictor in the general linear model, J. Statist. Plann. Inference, 139 (2009), 1522-1529.
• [14] X. Q. Liu, J. Y. Rong, X. Y. Liu, Best linear unbiased prediction for linear combinations in general mixed linear models, J. Multivariate Anal., 99 (2008), 1503-1517.
• [15] X. Liu, Q. W. Wang, Equality of the BLUPs under the mixed linear model when random components and errors are correlated, J. Multivariate Anal., 116 (2013), 297-309.
• [16] G. K. Robinson, That BLUP is a good thing: the estimation of random effects (with discussion on pp. 32-51), Stat. Sci., 6 (1991), 15-51.
• [17] Y. Tian, A new derivation of BLUPs under random-effects model, Metrika, 78 (2015), 905-918.
• [18] Y. Tian, B. Jiang, An algebraic study of BLUPs under two linear random-effects models with correlated covariance matrices, Linear Multilinear Algebra, 64 (12) (2016), 2351-2367.
• [19] Q. W. Wang, X. Liu, The equalities of BLUPs for linear combinations under two general linear mixed models, Commun. Stat.–Theory and Methods, 42 (2013), 3528-3543.
• [20] J. K. Baksalary, S. Kala, Linear transformations preserving best linear unbiased estimators in a general Gauss–Markoff model, Ann. Stat., 9 (1981), 913-916. [21] N. G¨uler, On relations between BLUPs under two transformed linear random-effects models, Communications in Statistics–Simulation and Computation, (2020), doi:10.1080/03610918.2020.1757709.
• [22] E. P. Liski, G. Trenkler, J. Grob, Estimation from transformed data under the linear regression model, Statistics, 29 (1997), 205-219.
• [23] C. H. Morrell, J. D. Pearson, L. J. Brant, Linear transformations of linear mixed-effects models, Am Stat., 51 (1997), 338-343.
• [24] J. Shao, J. Zhang, A transformation approach in linear mixed-effects models with informative missing responses, Biometrika, 102 (2015), 107-119.
• [25] Y. Tian, On properties of BLUEs under general linear regression models, J. Statist. Plann. Inference, 143 (2013), 771-782.
• [26] Y. Tian, Transformation approaches of linear random-effects models, Stat. Methods Appl., 26 (4) (2017), 583-608.
• [27] Y. Tian, C. Liu, Some equalities for estimations of variance components in a general linear model and its restricted and transformed models, Multivariate Anal., 101 (2010), 1959-1969.
• [28] Y. Tian, S. Puntanen, On the equivalence of estimations under a general linear model and its transformed models, Linear Algebra Appl., 430 (2009),2622-2641.
• [29] I. S. Alalouf, G. P. H. Styan, Characterizations of estimability in the general linear model, Ann. Stat., 7 (1979), 194-200.
• [30] A. S. Goldberger, Best linear unbiased prediction in the generalized linear regression model, J. Amer. Statist. Assoc., 57 (1962), 369-375.
• [31] S. Puntanen, G. P. H. Styan, J. Isotalo, Matrix Tricks for Linear Statistical Models: Our Personal Top Twenty, Springer, Heidelberg, 2011.