El impacto de especificar incorrectamente la distribución de los efectos aleatorios en las estimaciones de modelos lineales generalizados mixtos

• Autores: Diana Arango Botero, Freddy Hernández Barajas
• Localización: Comunicaciones en Estadística, ISSN 2027-3355, ISSN-e 2339-3076, Vol. 10, Nº. 2, 2017, págs. 247-280
• Idioma: español
• DOI: 10.15332/2422474x.3267
• Títulos paralelos:
  • The impact of misspecifying random efects distribution on the estimation of generalized linear mixed models
• Enlaces
  • Texto completo (pdf)
• Resumen
  • español

    La inferencia en modelos lineales generalizados mixtos está basada principalmente en la teoría de máxima verosimilitud, la cual asume que las estructuras tanto para la parte de los efectos fijos como de los efectos aleatorios están correctamente especificadas. Algunos autores han mostrado la sensibilidad de las estimaciones de los efectos fijos a especificaciones incorrectas de los efectos aleatorios. El objetivo de esta investigación es identificar, vía simulación, el impacto de la especificación incorrecta de la distribución de los efectos aleatorios en los modelos lineales generalizados mixtos, específicamente para los casos de las distribuciones Poisson y Binomial Negativa  

  • English

    Inference in generalized linear mixed models is often based on maximum likelihood theory, which assumes that structures of both fixed effects and random effects is correctly specified. Some authors have shown sensitivity of estimates of fixed effects to random-effects misspecifications. This research aims to identify, using simulation, the impact of misspecifying random-effects distribution in generalized linear mixed models, specifically for the cases of Poisson and Negative Binomial distributions.  

• Referencias bibliográficas
  • Alonso, A., Litière, S. & Molenberghs, G. (2008), 'A family of tests to detect
  • misspecifications in the random-effects structure of generalized linear mixed
  • models', Computational statistics and data analysis 52(9), 4474_4486.
  • Alonso, A., Litière, S. & Molenberghs, G. (2010), 'Testing for misspecification in
  • generalized linear mixed models', Biostatistics 11(4), 771_786.
  • Alonso, A., Milanzi, E., Molenberghs, G., Buyck, C. & Bijnens, L. (2015), 'A
  • new modeling approach for quantifying expert opinion in the drug discovery
  • process', Statistics in medicine 34(9), 1590_1604.
  • Bolker, B. M., Brooks, M. E., Clark, C. J., Geange, S. W., Poulsen, J. R., Stevens,
  • M. H. H. & White, J. S. (2009), 'Generalized linear mixed models: a practical
  • guide for ecology and evolution', Trends in ecology and evolution 24(3), 127_
  • Cook, R. J., Lee, K. A. & Li, H. (2007), 'Non-inferiority trial design for recurrent
  • events', Statistics in medicine 26(25), 4563_4577.
  • DeGroot, M. H. & Schervish, M. J. (1988), Probabilidad y estadística, Editorial
  • Addison Wesley, Mexico.
  • Fabio, L. C., Paula, G. A. & De Castro, M. (2012), 'A Poisson mixed model with
  • nonnormal random effect distribution', Computational Statistics and Data
  • Analysis 56(6), 1499_1510.
  • Fitzmaurice, G. M., Laird, N. M. & Ware, J. H. (2011), Applied longitudinal analy-
  • sis, segunda edn, John Wiley and Sons, Boston, Massachusetts.
  • Gad, A. M. & El Kholy, R. B. (2012), 'Generalized Linear mixed models for Longitudinal
  • Data', International Journal of Probability and Statistics 1(3), 41_47.
  • Heagerty, P. J. & Kurland, B. F. (2001), 'Misspecified maximum likelihood estimates
  • and generalised linear mixed models', Biometrika 88(4), 973_985.
  • Hilbe, J. M. (2011), Negative binomial regression, Cambridge University Press.
  • Huang, X. (2009), 'Diagnosis of Random-Effect Model Misspecification in Generalized
  • Linear Mixed Models for Binary Response', Biometrics 65(2), 361_368.
  • Komárek, A. & Lesaffre, E. (2008), 'Generalized linear mixed model with a penalized
  • Gaussian mixture as a random effects distribution', Computational
  • Statistics and Data Analysis 52(7), 3441_3458.
  • Kondo, Y., Zhao, Y. & Petkau, J. (2015), 'A flexible mixed-effect negative binomial
  • regression model for detecting unusual increases in MRI lesion counts
  • in individual multiple sclerosis patients', Statistics in medicine 34(13), 2165_
  • Litière, S., Alonso, A. & Molenberghs, G. (2007), 'Type I and Type II Error
  • Under Random-Effects Misspecification in Generalized Linear Mixed Models',
  • Biometrics 63(4), 1038_1044.
  • Litière, S., Alonso, A. & Molenberghs, G. (2008), 'The impact of a misspecified
  • random-effects distribution on the estimation and the performance of inferential
  • procedures in generalized linear mixed models', Statistics in medicine
  • (16), 3125_3144.
  • McCulloch, C. E. & Neuhaus, J. M. (2011), 'Misspecifying the shape of a random
  • effects distribution: why getting it wrong may not matter', Statistical science
  • pp. 388_402.
  • Milanzi, E., Alonso, A. & Molenberghs, G. (2012), 'Ignoring overdispersion in
  • hierarchical loglinear models: Possible problems and solutions', Statistics in
  • medicine 31(14), 1475_1482.
  • Molenberghs, G. & Verbeke, G. (2005), Models for Discrete Longitudinal Data.
  • Springer Series in Statistics, Springer.
  • Neuhaus, J. M., Hauck, W. W. & Kalbfleisch, J. D. (1992), 'The effects of mixture
  • distribution misspecification when fitting mixed-effects logistic models',
  • Biometrika 79(4), 755_762.
  • Neuhaus, J. M. & McCulloch, C. E. (2006), 'Separating between-and within-cluster
  • covariate effects by using conditional and partitioning methods', Journal of
  • the Royal Statistical Society: Series B (Statistical Methodology) 68(5), 859_
  • Neuhaus, J. M. & McCulloch, C. E. (2011a), 'Estimation of covariate effects in
  • generalized linear mixed models with informative cluster sizes', Biometrika
  • (1), 147_162.
  • Neuhaus, J. M. & McCulloch, C. E. (2011b), 'The effect of misspecification of random
  • e_ects distributions in clustered data settings with outcome-dependent
  • sampling', Canadian Journal of Statistics 39(3), 488_497.
  • Neuhaus, J. M., McCulloch, C. E. & Boylan, R. (2011), 'A Note on Type II Error
  • Under Random Effects Misspecification in Generalized Linear Mixed Models',
  • Biometrics 67(2), 654_656.
  • Neuhaus, J. M., McCulloch, C. E. & Boylan, R. (2012), 'Estimation of covariate
  • effects in generalized linear mixed models with a misspecified distribution of
  • random intercepts and slopes', Statistics in medicine 32(14), 2419_2429.
  • Spiessens, B., Lesaffre, E., Verbeke, G. & Kim, K. (2002), 'Group Sequential Methods
  • for an Ordinal Logistic Random-Effects Model Under Misspecification',
  • Biometrics 58(3), 569_575.
  • Tsonaka, R., Rizopoulos, D., Verbeke, G. & Lesa_re, E. (2010), 'Nonignorable models
  • for intermittently missing categorical longitudinal responses', Biometrics
  • (3), 834_844.
  • Valencia, A. (2014), 'El uso de la distribución gh en riesgo operativo', Contaduría
  • y administración 59(1), 123_148.
  • Verbeke, G. & Lesaffre, E. (1997), 'The effect of misspecifying the random-effects
  • distribution in linear mixed models for longitudinal data', Computational Statistics and Data Analysis 23(4), 541_556.
  • Verbeke, G. & Molenberghs, G. (2013), 'The gradient function as an exploratory
  • goodness-of-_t assessment of the random-effects distribution in mixed models',
  • Biostatistics 14(3), 477.
  • Xiang, L., Yau, K. K. & Lee, A. H. (2012), 'The robust estimation method for a
  • _nite mixture of Poisson mixed-effect models', Computational Statistics and
  • Data Analysis 56(6), 1994_2005.
  • Zhao, Y., Li, D. K., Petkau, A. J., Riddehough, A. & Traboulsee, A. (2014), 'Detection
  • of unusual increases in MRI lesion counts in individual multiple sclerosis
  • patients', Journal of the American Statistical Association 109(505), 119_132.