Estimation, Testing, and Prediction Regions of the Fixed and Random Effects by Solving the Henderson’s Mixed Model Equations

Viktor Witkovský

doi:10.2478/v10048-012-0033-6

.blurhash-client-img { display: none !important; }

Estimation, Testing, and Prediction Regions of the Fixed and Random Effects by Solving the Henderson’s Mixed Model Equations

Measurement Science Review

Volume 12 (2012): Issue 6 (December 2012)

By: Viktor Witkovský

Open Access

|Dec 2012

Abstract

We present a brief overview of the methods for making statistical inference (testing statistical hypotheses, construction of confidence and/or prediction intervals and regions) about linear functions of the fixed effects and/or about the fixed and random effects simultaneously, in conventional simple linear mixed model. The presented approach is based on solutions from the Henderson’s mixed model equations.

References

[1] Alnosaier, W.S. (2007). Kenward-Roger Approximate F Test for Fixed Effects in Mixed Linear Models. Dissertation Thesis submitted to Oregon State University, April 25, 2007. http://ir.library.oregonstate.edu
Search in Google Scholar
[2] Arendacká, B. (2007). Fiducial generalized pivots for a variance component vs. an approximate confidence Interval. Measurement Science Review 7 (6), 55 - 63.
Search in Google Scholar
[3] Arendacká, B. (2012). Approximate interval for the between group variance under heteroscedasticity. Journal of Statistical Computation & Simulation 82 (2), 209 - 218.10.1080/00949655.2011.606548
Search in Google Scholar
[4] Arendacká, B. (2012). A note on fiducial generalized pivots for σ2 A in one-way heteroscedastic ANOVA with random effects. Statistics 46 (4), 489 - 504.
Search in Google Scholar
[5] Caliński, T., Kageyama, S. (2008). On the analysis of experiments in affine resolvable designs. Journal of Statistical Planning and Inference 138, 3350 - 3356.10.1016/j.jspi.2007.04.036
Search in Google Scholar
[6] Chvosteková, M., Witkovský, V. (2009). Exact likelihood ratio test for the parameters of the linear regression model with normal errors. Measurement Science Review 9 (1), 1 - 8.10.2478/v10048-009-0003-9
Search in Google Scholar
[7] Cui, X., Churchill, G.A. (2003). How many mice and how many arrays? Replication of cDNA microarray experiments. In Lin, S.M. and Allred, E.T. (eds), Methods of Microarray DataAnalysis III, New York: Kluwer.
Search in Google Scholar
[8] Cui, X., Hwang, J.T.G, Qiu, J., Blades, N.J., Churchill, G.A. (2005). Improved statistical tests for differential gene expression by shrinking variance components estimates. Biostatistics 6 (1), 59 - 75.10.1093/biostatistics/kxh01815618528
Search in Google Scholar
[9] Cui, X., Affourtit, J., Shockley, K.R., Woo, Y., Churchill, G.A. (2006). Inheritance patterns of transcript levels in F1 hybrid mice. Genetics 174, 627 - 637.10.1534/genetics.106.060251160207716888332
Search in Google Scholar
[10] Das, K., Jiang, J., Rao, J.N.K. (2004). Mean squared error of empirical predictor. Annals of Statistics 32, 818 -- 840.10.1214/009053604000000201
Search in Google Scholar
[11] Domotor, Z. (2012). Algebraic frameworks for measurement in the natural sciences. Measurement Science Review 12 (6), 213 - 233.10.2478/v10048-012-0032-7
Search in Google Scholar
[12] Elston, D.A. (1998). Estimation of denominator degrees of freedom of F-distributions for assessing Wald statistics for fixed-effect factors in unbalanced mixed models. Biometrics 54 (3), 1085 - 1096.10.2307/2533859
Search in Google Scholar
[13] Fai, A.H.T., Cornelius, P.L. (1996). Approximate F-tests of multiple degree of freedom hypotheses in generalized least squares analyses of unbalanced split-plot experiments. Journal of Statistical Computing and Simulation 54, 363 - 378.
Search in Google Scholar
[14] Fonseca, M., Mathew, T., Mexia, J.T., Zmyślony, R. (2007). Tolerance intervals in a two-way nested model with mixed or random effects. Statistics 41 (4), 289 - 300.10.1080/02331880701270648
Search in Google Scholar
[15] Gelman, A. (2005). Analysis of variance: Why it is more important than ever. The Annals of Statistics 33 (1), 1 - 31.10.1214/009053604000001048
Search in Google Scholar
[16] Giesbrecht, F.G., Burns, J.C. (1985). Two-stage analysis based on a mixed model: Large sample asymptotic theory and smallsample simulation results. Biometrics 41, 477 - 486.10.2307/2530872
Search in Google Scholar
[17] Hartley, H.O., Rao, J.N.K. (1967). Maximum-likelihood estimation for the mixed analysis of variance model. Biometrika 54, 93 - 108.10.1093/biomet/54.1-2.93
Search in Google Scholar
[18] Hartung, J., Knapp, G., Sinha, B.K. (2008). Statistical Meta-Analysis with Applications, New York: Wiley.10.1002/9780470386347
Search in Google Scholar
[19] Harville, D.A. (1977). Maximum likelihood approaches to variance component estimation and to related problems. Journal of the American Statistical Association 72, 320 - 38.10.1080/01621459.1977.10480998
Search in Google Scholar
[20] Harville, D.A. (1985). Decomposition of prediction error. Journal of the American Statistical Association 80, 132 - 138.10.1080/01621459.1985.10477152
Search in Google Scholar
[21] Harville, D.A., Jeske, D.R. (1992). Mean squared error of estimation or prediction under a general linear model. Journal of the American Statistical Association 87, 724 - 731.10.1080/01621459.1992.10475274
Search in Google Scholar
[22] Harville, D.A. (2008). Accounting for the estimation of variances and covariances in prediction under general linear model: An overview. Tatra Mountains Mathematical Publications 39, 1 - 15.
Search in Google Scholar
[23] Henderson, C.R. (1953). Estimation of variance and covariance components Biometrics 9 (2), 226 - 252.10.2307/3001853
Search in Google Scholar
[24] Herdahl, M. (2008). Linear mixed model for compressor head and flow data with an application. Department of Mathematical Sciences, Norwegian University of Science and Technology (NTNU), Norway, June 2008. http://ntnu.diva-portal.org.
Search in Google Scholar
[25] Jeske, D.R., Harville, D.A., (1988). Prediction-interval procedures and (fixed-effects) confidence-interval procedures for mixed linear models. Communications in Statistics - Theory and Methods 17, 1053 - 1087.10.1080/03610928808829672
Search in Google Scholar
[26] Jiang, J. (1999). On unbiasedness of the empirical BLUE and BLUP. Statistical and Probability Letters 41 (1999), 19 - 24.
Search in Google Scholar
[27] Kackar, R.N., Harville, D.A. (1981). Unbiasedness of two-stage estimation and prediction procedures for mixed linear models, Communications in Statistics - Theory and Methods 10, 1249 - 1261.10.1080/03610928108828108
Search in Google Scholar
[28] Kackar, R.N., Harville, D.A. (1984). Approximations for standard errors of estimators of fixed and random effects in mixed linear models. Journal of the American Statistical Association 79, 853 - 862.
Search in Google Scholar
[29] Kenward, M.G., Roger, J.H. (1997). Small sample inference for fixed effects from restricted maximum likelihood, Biometrics 53, 983 - 997.10.2307/2533558
Search in Google Scholar
[30] Kenward, M.G., Roger, J.H. (2009). An improved approximation to the precision of fixed effects from restricted maximum likelihood. Computational Statistics and Data Analysis 53 2583 - 2595.10.1016/j.csda.2008.12.013
Search in Google Scholar
[31] Krishnamoorthy, K., Mathew, T. (2009). Statistical Tolerance Regions: Theory, Applications, and Computation, New York: Wiley.10.1002/9780470473900
Search in Google Scholar
[32] Laird, N.M., Lange, N., Stram, D. (1987). Maximum likelihood computations with repeated measures: Application of the EM algorithm. Journal of the American Statistical Association 82, 97 - 105.10.1080/01621459.1987.10478395
Search in Google Scholar
[33] La Motte, L.R. (1973). Quadratic estimation of variance components. Biometrics 29, 311 - 330.10.2307/2529395
Search in Google Scholar
[34] Lindstrom, M.J., Bates, D.M. (1988). Newton-Raphson and EM algorithms for linear mixed-effects models for repeated measures data. Journal of the American Statistical Association 83, 1014 - 1022.
Search in Google Scholar
[35] Littell, R.C., Milliken, G.A., Stroup, W.W., Wolfinger, R.D., Schabenberger, O. (2006). SAS for Mixed Models, Second Edition, Cary, NC: SAS Institute Inc.
Search in Google Scholar
[36] McCulloch, C.E., Searle, S.R. (2001). Generalized, Linear, and Mixed Models, New York: Wiley.10.1002/9780470057339.vag009
Search in Google Scholar
[37] McLean, R.A., Sanders, W.L. (1988). Approximating degrees of freedom for standard errors in mixed linear models. In: Proceedings of the Statistical Computing Section, Alexandria, VA: American Statistical Association, 50 - 59.
Search in Google Scholar
[38] McLean, R.A., Sanders, W.L., Stroup, W.W. (1991). A unified approach to mixed linear models. The American Statistician 45, 54 - 64.
Search in Google Scholar
[39] Patterson, H.D., Thompson, R. (1971). Recovery of interblock information when block sizes are unequal. Biometrika 58, 545 - 554.10.1093/biomet/58.3.545
Search in Google Scholar
[40] Pinheiro, J.C., Bates, D.M. (2000): Mixed-Effects Models in Sand S-PLUS. Springer-Verlag, New York.10.1007/978-1-4419-0318-1
Search in Google Scholar
[41] Prasad, N.G.N., Rao, J.N.K. (1990). The estimation of the mean squared error of small area estimators. Journal of the American Statistical Association 85, 163 - 171.10.1080/01621459.1990.10475320
Search in Google Scholar
[42] Rao, C.R. (1972). Estimation of variance and covariance components in linear models. Journal of the American Statistical Association 67, 112 -- 115.10.1080/01621459.1972.10481212
Search in Google Scholar
[43] Rao, C.R., Kleffe, J. (1988). Estimation of Variance Components and Applications. North-Holland Publishing Company, Amsterdam.
Search in Google Scholar
[44] Robinson, G.K. (1991). That BLUP is a good thing: The estimation of random effects. Statistical Science 6, 15 - 51.
Search in Google Scholar
[45] SAS Institute, Inc. (2012), SAS/STAT 9.2 User’s Guide The MIXED Procedure. Online Help, Cary, NC: SAS Institute.
Search in Google Scholar
[46] Satterthwaite, F.E. (1941). Synthesis of variance. Pyschometrika 6, 309 - 316.10.1007/BF02288586
Search in Google Scholar
[47] Satterthwaite, F.E. (1946). An approximate distribution of estimates of variance components. Biometrics Bulletin 2 (6), 110 -114.10.2307/3002019
Search in Google Scholar
[48] Savin, A., Wimmer, G., Witkovský, V. (2003). On Kenward- Roger confidence intervals for common mean in interlaboratory trials. Measurement Science Review 3, 53 - 56.
Search in Google Scholar
[49] Searle, S.R., Casella, G. McCulloch, C.E. (1992). Variance Components. John Wiley & Sons, New York.10.1002/9780470316856
Search in Google Scholar
[50] Schaalje, B.G., McBride, J.B., Fellingham, G.W. (2001). Approximations to distributions of test statistics in complex mixed linear models using SAS Proc MIXED. In: SUGI 26 Proceedings,Statistics, Data Analysis and Data Mining Section, Paper262, 1 - 5.
Search in Google Scholar
[51] Schulz, E., Tiemann, L., Witkovský, V., Schmidt, P., Ploner, M. (2012). Gamma oscillations are involved in the sensorimotor transformation of pain. Journal of Neurophysiology 108, 1025 - 1031.10.1152/jn.00186.201222623490
Search in Google Scholar
[52] Širková, L.,Witkovský, V. (2001). On testing variance components in unbalanced mixed linear model. Applications of Mathematics 46 (3), 191 - 213.10.1023/A:1013739907119
Search in Google Scholar
[53] Štulajter, F. (2002). The MSE of the BLUP in a finite discrete spectrum LRM. Tatra Mountains Mathematical Publications 26, 125 -- 131.
Search in Google Scholar
[54] Štulajter, F. (2002). Predictions in Time Series Using Regression Models, Springer-Verlag, New York.10.1007/978-1-4757-3629-8
Search in Google Scholar
[55] Tuček, P., Tučková, M., Fišerová, E., Tuček, J., Kubáček, L. (2012). Design of experiment for measurement of Langevin function. Measurement Science Review 12 (4), 121 - 127.10.2478/v10048-012-0019-4
Search in Google Scholar
[56] Volaufová J. (2005). Statistical methods in biomedical research and measurement science. Measurement Science Review 5, Section 1, 1 - 10.
Search in Google Scholar
[57] Volaufová J., Witkovský, V. (1992). Estimation of variance components in mixed linear models. Applications of Mathematics 37 (2), 139 - 148.10.21136/AM.1992.104497
Search in Google Scholar
[58] Volaufová J., Witkovský, V. (1992). Least-squares and minimum MSE estimators of variance components in mixed linear models. Biometrical Journal 33 (8), 923 - 936.
Search in Google Scholar
[59] Volaufová J., Witkovský, V. (2012). On exact inference in linear models with two variance-covariance components. TatraMountains Mathematical Publications 51, 173 - 181.10.2478/v10127-012-0017-9
Search in Google Scholar
[60] Wolfinger, R.D., Tobias, R.D., Sall, J. (1994). Computing gaussian likelihoods and their derivatives for general linear mixed models. SIAM Journal on Scientific Computing 15 (6), 1294 -1310.10.1137/0915079
Search in Google Scholar
[61] Wimmer G., Witkovský, V. (2003). Between group variance component interval estimation for the unbalanced heteroscedastic one-way random effects model. Journal of Statistical Computation and Simulation 73 (5), 333 - 346.10.1080/0094965021000038940
Search in Google Scholar
[62] Wimmer G.,Witkovský, V. (2007). Linear comparative calibration with correlated measurements. Kybernetika 43 (4), 443 -452.
Search in Google Scholar
[63] Wimmer G., Witkovský, V. (2007). Univariate linear calibration via replicated errors-in-variables model. Journal of Statistical Computation and Simulation 77 (3), 213 - 227.10.1080/10629360600679433
Search in Google Scholar
[64] Wimmer G.,Witkovský, V. (2011). Note on a calibration problem: Selected results and extensions of professor Kubáˇcek’s research. Acta Universitatis Palackianae Olomucensis, Facul-tas Rerum Naturalium, Mathematica 50 (2), 123 - 130.
Search in Google Scholar
[65] Witkovský, V. (1996). On variance-covariance components estimation in linear models with AR(1). Acta Mathematica UniviversitatisComenianae 65 (1), 129 - 139.
Search in Google Scholar
[66] Witkovský, V. (1998). Estimation of variance components with constraints. Journal of Statistical Planning and Inference 69 (1), 81 - 87.10.1016/S0378-3758(97)00127-4
Search in Google Scholar
[67] Witkovský, V. (1998). Modified minimax quadratic estimation of variance components. Kybernetika 34 (5), 535 - 543.
Search in Google Scholar
[68] Witkovský, V. (2002). MATLAB algorithm mixed.m for solving Henderson’s mixed model equations. Technical Report, Institute of Measurement Science, Slovak Academy of Sciences, Bratislava, 2002. http://www.mathworks.com/matlabcentral/fileexchange/200-mixed.
Search in Google Scholar
[69] Witkovský, V. (2005). Comparison of some exact and approximate interval estimators for common mean. Measurement ScienceReview 5 (1), 19 - 22.
Search in Google Scholar
[70] Witkovský, Savin, A., Wimmer G. (2003). On small sample inference for common mean in heteroscedastic one-way model. Discussiones Mathematicae Probability and Statistics 23 (2), 123 - 145.
Search in Google Scholar
[71] Witkovský, V., Wimmer G. (2001). On statistical models for consensus values. Measurement Science Review 1 (1), 33 - 36.
Search in Google Scholar
[72] Witkovský, V.,Wimmer G. (2003). Consensus mean and interval estimators for the common mean. Tatra Mountains MathematicalPublications 26 (1), 183 - 194.
Search in Google Scholar
[73] Witkovský, V., Wimmer G. (2007). Confidence interval for common mean in interlaboratory comparisons with systematic laboratory biases. Measurement Science Review 7 (6), 64 - 73.
Search in Google Scholar
[74] Wu, H., Yang, H., Churchill, G.A. (2012). R/MAANOVA: Anextensive R environment for the analysis of microarray experiments. http://www.bioconductor.org
Search in Google Scholar

Articles in this issue

DOI: https://doi.org/10.2478/v10048-012-0033-6 | Journal eISSN: 1335-8871

Journal RSS Feed

Language: English

Page range: 234 - 248

Published on: Dec 15, 2012

Published by: Slovak Academy of Sciences, Institute of Measurement Science

In partnership with: Paradigm Publishing Services

Publication frequency: Volume open

Keywords:

Linear mixed model,

mixed model equations,

fixed effects,

random effects,

REML,

BLUP,

EBLUP,

MSE,

Satterthwaite approximation,

Fai-Cornelius approximation,

Harville-Jeske and Prasad-Rao approximation,

Kenward-Roger approximation

Related subjects:

Engineering,

Electrical engineering,

Control engineering, metrology and testing

© 2012 Viktor Witkovský, published by Slovak Academy of Sciences, Institute of Measurement Science
This work is licensed under the Creative Commons License.

Volume 12 (2012): Issue 6 (December 2012)