Exploration of Extended Models for Overdispersed, Repeated Time-to-Event Data

Martial
Luyts

Onderzoek naar nieuwe modelleringstechnieken om overlevingstijden bij patienten betrouwbaarder te schatten is een must, maar waarom?

In statistiek komt het vaak voor dat uitkomsten een niet-normaal verdeeld patroon vertonen. Het analyseren van deze types wordt traditioneel gedaan met verdelingen uit de zo-genaamde exponentiële familie, waarbij de Poisson voor aantallen en de Bernoulli verdeling voor binaire data de meest gekende zijn. Door de aanwezigheid van complexere structuren in klinische studies (bv. bij het onderzoeken of een nieuw medicijn al dan niet effect heeft) kan het voorkomen dat een slechte schatting wordt gevormd met deze modellen. De nood aan uitbreidingen is daarom voorhanden. Twee redenen die een belangrijke rol spelen bij deze conclusie zijn (1) de aanwezig van overdispersie, betekende dat de variabiliteit in de data niet adequaat wordt beschreven door de statistische modellen, en (2) de mogelijke hiërarchische structuren in de data, afkomstig door clusteringen in de data, welke op hun beurt, resulteert uit herhaalde metingen van de uitkomst. In klinische studies, bijvoorbeeld, komt het vaak voor dat patïenten worden gemeten over tijd (bv. de hartslag).


In het verleden is veel onderzoek verricht naar het vinden van gepaste, uitgebreidere modelleringstechnieken die beide aspecten in rekening brengen. Terwijl deze twee aspecten vaak afzonderlijk werden behandeld (Hinde en Demétrio, 1998ab; Verbeke et al, 2000; Molenberghs et al, 2005), ontwikkelde Molenberghs et al (2010) een elegant raamwerk dat de mogelijkheid biedt om beide aspecten gelijktijdig in rekening te brengen d.m.v. twee afzonderlijke verzamelingen van random effecten, en zelfs apart te behandelen. Deze twee random-effecten brengen overdispersie en hiërarchische structuren in rekening, welke voor een meer accurater precisie zorgt, en dus resulteert in betrouwbaardere conclusies. Terwijl vroeger de kans groter was dat farmaceutische bedrijven een goed medicijn verwierp, zorgt dit raamwerk voor een reductie van deze foute conclusies. 

In deze thesis wordt specifieke focus gelegd op overlevingstijden (bv. wanneer een patient een astma aanval krijgt). Door de flexibele structuur van het raamwerk zijn vele uitbreidingen mogelijk voor onderzoek. Naast univariate analyses, waarbij slechts 1 uitkomst (bv. de astma aanvallen van een patient) wordt gemodelleerd, kunnen gezamenlijke analyses plaatsvinden, waarbij verschillende types van uitkomsten tegelijkertijd worden gemodelleerd. In een cardiologische studie, bijvoorbeeld, waarin onderzoekers gebruik maken van telemonitoring (een techniek waarmee patïenten vanop afstand worden gevolgd) om bloeddruk te meten op dagelijkse basis, worden vaak gecombineerd met additionele gegevens zoals hartslag en gewicht, naast tijd tot heropname. 

Naast de theoretische discussie, sluit dit werk af met een uitgebreide analyse van de astma dataset (Duchateau en Janssen, 2008). Dus laat je verleiden in de statistische wereld van farmacie, en overtuig jezelf ervan dat verder onderzoek noodzakelijk is in het verrijken en concluderen van correctere resultaten binnen de academische en professionele wereld!  

Bibliografie

References

  1. [1]  Agresti A. Categorical data analysis (2nd ed.). John Wiley & Sons, Inc, New York, 2002.

  2. [2]  Creemers A., Hens N., Aerts M., Molenberghs G., Verbeke G., and Kenward M. G. Sensitivity analysis for shared-parameter models for incomplete longitudinal out- comes. Biometrical Journal, 52(1):111–125, 2010.

  3. [3]  Creemers A., Hens N., Aerts M., Molenberghs G., Verbeke G., and Kenward M. G. A sensitivity analysis for shared-parameter models for incomplete longitudinal out- comes. Biometrical Journal, 52(1):111–125, 2010.

  4. [4]  Creemers A., Hens N., Aerts M., Molenberghs G., Verbeke G., and Kenward M. G. Generalized shared-parameter models and missingness at random. Statistical Mod- elling, 11(4):279–310, 2011.

  5. [5]  Efendi A. and Molenberghs G. A combined gamma frailty and normal random- effects model for repeated, overdispersed time-to-event data. Journal of Biophar- maceutical Statistics, 13(6):1420–1434, 2013.

  6. [6]  Efendi A. and Molenberghs G. A multilevel model for hierarchical, repeated, overdis- persed time-to-event outcomes and its estimation strategies. Journal of Biophar- maceutical Statistics, 23(6):1420–1434, 2013.

  7. [7]  Efendi A., Molenberghs G., Njagi E. N., and Dendale P. A joint model with marginal interpretation for longitudinal continuous and time-to-event outcomes. Statistical Modelling, 2013.

  8. [8]  Efendi A., Molenberghs G., and Iddi S. A marginalized combined model for re- peated, overdispersed time-to-event outcomes. Communication in Statistics - The- ory and Methods, 43(22):4806–4828, 2014.

  9. [9]  Efendi A., Verbeke G., and Molenberghs G. A goodness-of-fit test for the random- effects distribution in mixed models. Statistical Methods in Medical Research, 2013.

  10. [10]  Gelman A. and Rubin D. B. Inference from iterative simulation using multiple sequences. Statistical Science, 7(4):457–511, 1992.

  11. [11]  Gelman A., Carlin J. B., Stern H. S., and Rubin D. B. Bayesian data analysis. Texts in Statistical Science, Chapman & Hall, London, 1995.

  12. [12]  Ivanova A., Molenberghs G., and Verbeke G. A model for overdispersed hierarchical ordinal data. Statistical Modelling, 14(5):399–415, 2014.

  1. [13]  Skrondal A. and Rabe-Hesketh S. Generalized latent variable modeling. Chapman & Hall/CRC, London, 2004.

  2. [14]  Tsiatis A. and Davidian M. Joint modeling of longitudinal and time-to-event data: an overview. Statistica Sinica, 14(1):809–834, 2004.

  3. [15]  Zuur A., Leno E. N., and Smith G. M. Analysing ecological data. Spinger, New York, 2007.

  4. [16]  Zuur A., Leno E. N., Smith G. M., Saveliev A. A., and Walker N. Mixed effects models and extensions in ecology with R. Spinger, New York, 2009.

  5. [17]  Lawson A. B. and Browne W. J. Disease mapping with WinBUGS and MLwiN (1st ed.) (Statistics in Practice). John Wiley & Sons, Inc, New York, 2003.

  6. [18]  Gelfand A. E. and Smith A. F. M. Sampling-based approaches to calculating marginal densities. Journal of the American Statistical Association, 85(410):398– 409, 1990.

  7. [19]  Ghebretinsae A. H., Faes C., Molenberghs G., Geys H., and Van der Leede B. J. Joint modeling of hierarchically clustered and overdispersed non-gaussian continu- ous outcomes for comet assay data. Pharmaceutical Statistics, 11(6):449–455, 2012.

  8. [20]  Ghebretinsae A. H., Faes C., Molenberghs G., De Boeck M., and Geys H. A bayesian, generalized frailty model for comet assays. Journal of Biopharmaceutical Statistics, 23(3):618–636, 2013.

  9. [21]  Lemonte A. J. and A. G. Patriota. Multivariate elliptical models with general parameterization. Statistical Methodology, 8(4):389–400, 2011.

  10. [22]  Engel B. and A. Keen. A simple approach for the analysis of generalized linear mixed models. Statistica Neerlandica, 48(1):1–22, 1994.

  11. [23]  Jφrgensen B. Exponential dispersion models (with discussion). Journal of the Royal Statistical Society, Series B, 49(2):127–162, 1987.

  12. [24]  Arnold B. C. and Strauss D. Pseudolikelihood estimation: Some examples. The Indian Journal of Statistics, Series B (1960-2002), 53(2):233–243, 1991.

  13. [25]  Lindsay B. G. Composite likelihood methods. Contemporary Mathematics, 80(1):221–239, 1988.

  14. [26]  Spearman C. “general intelligence,” objectively determined and measured. The American Journal of Psychology, 15(2):201–292, 1904.

  15. [27]  Varin C. On composite marginal likelihoods. Advances in Statistical Analysis, 92(1):233–243, 2008.

  16. [28]  Dean C. B. Estimating equations for mixed-poisson models. Estimating Functions, V.P. Godambe (Ed.), 1(1):35–46, 1991.

  17. [29]  Dean C. B. and Nielsen J. D. Generalized linear mixed models: A review and some extensions. Lifetime Data Analysis, 13(4):497–512, 2007.

  1. [30]  Geyer C. J. Practical markov chain monte carlo. Statistical Science, 7(4):473–483, 1992.

  2. [31]  Wintrebert C. M. A., Zwinderman A. H., Cam E., Pradel R., and van Houwelingen J. C. Joint modelling of breeding and survival in the kittiwake using frailty models. Ecological Modelling, 181(2-3):203–213, 2005.

  3. [32]  Clayton D. and Rasbash J. Estimation in large crossed random-effect models by data augmentation. Journal of the Royal Statistical Society, Series A, 162(3):425– 436, 1999.

  4. [33]  Cox D. and Reid N. A note on pseudolikelihood constructed from marginal densities. Biometrika, 91(3):729–737, 2004.

  5. [34]  Lambert D. Zero-inflated poisson regression, with an application to defects in man- ufacturing. Technometrics, 34(1):1–14, 1992.

  6. [35]  Rizopoulos D. Dynamic predictions and prospective accuracy in joint models for longitudinal and time-to-event data. Biometrics, 67(3):819–829, 2011.

  7. [36]  Rizopoulos D. Joint models for longitudinal and time-to-event data. Boca Raton: Chapman and Hall/CRC, 2012a.

  8. [37]  Rizopoulos D., Verbeke G., and Molenberghs G. Shared parameter models under random effects misspecification. Biometrika, 95(1):63–74, 2008.

  9. [38]  Stegmueller D. How many countries for multilevel modeling? a comparison of fre- quentist and bayesian approaches. American Journal of Political Science, 57(3):748– 761, 2013.

  10. [39]  Hall D. B. Zero-inflated poisson and binomial regression with random effects: A case study. Biometrics, 56(4):1030–1039, 2000.

  11. [40]  Rubin D. B. Inference and missing data. Biometrika, 63(3):581–592, 1976.

  12. [41]  Rubin D. C., Hinton S., and Wenzel A. The precise time course of retention. Journal of Experimental Psychology: Learning, Memory, and Cognition, 25(5):1161–1176, 1999.

  13. [42]  Heitjan D. F. and Rubin D. B. Ignorability and coarse data. The Annals of Statistics, 19(4):2244–2253, 1991.

  14. [43]  Cox D. R. Regression models and life-tables (with discussion). Journal of the Royal Statistical Society, Series B, 34(2):187–220, 1972.

  15. [44]  Cox D. R. Some remarks on overdispersion. Biometrika, 70(1):269–274, 1983.

  16. [45]  Cox D. R. and Hinkley D. V. Theoretical statistics. Chapman & Hall, London,

    1974.

  17. [46]  Lesaffre E. and Lawson A. B. Bayesian biostatistics. John Wiley & Sons, Ltd, New York, 2012.

  1. [47]  Lesaffre E. and Verbeke G. Local influence in linear mixed models. Biometrics, 54(2):570–582, 1998.

  2. [48]  Norden E. H., Long S. R., Tung C. C., Yuan Y., and Bliven L. F. A non-gaussian statistical model for surface elevation of nonlinear random wave fields. Journal of Geophysical Research, 88(C12):7597–7606, 1983.

  3. [49]  Njagi E. N., Rizopoulos D., Molenberghs G., Dendale P., and Willekens K. A joint survival-longitudinal modelling approach for the dynamic prediction of rehos- pitalization in telemonitored chronic heart failure patients. Statistical Modelling, 13(3):179–198, 2013.

  4. [50]  Njagi E. N., Molenberghs G., Rizopoulus D., Verbeke G., Kenward M. G., Dendale P., and Willekens K. A flexible joint-modeling framework for longitudinal and time-to-event data with overdispersion. Statistical Methods in Medical Research, 0(0):1–16, 2013.

  5. [51]  Njagi E. N., Molenberghs G., Kenward M. G., Verbeke G., and Rizopoulus D. A characterization of missingness at random in a generalized shared-parameter joint modelling framework for longitudinal and time-to-event data, and sensitivity anal- ysis. Biometrical Journal, 56(6):1001–1015, 2013.

  6. [52]  Tuerlinckx F., Rijmen F., Molenberghs G., Verbeke G., Briggs D., Van Den Noort- gate W., Meulders M., and De Boeck P. Estimation and software. in p. de boeck & m. wilson (eds.). Explanatory item response models: A generalized linear and nonlinear approach, 12(1):343–373, 2004.

  7. [53]  Hildebrand F. B. Advanced calculus for applications. Prentice-Hall, Englewood Cliffs, 1962.

  8. [54]  D’Agostini G. Bayesian inference in processing experimental data: Principles and basic applications. Reports on Progress in Physics, 66(9):1383–1419, 2003.

  9. [55]  Frahm G. Generalized elliptical distributions: Theory and applications. Thesis, 2004.

  10. [56]  Molenberghs G., Michiels B., Kenward M. G., and Diggle P. J. Monotone missing data and pattern-mixture models. Statistica Neerlandica, 52(2):153–161, 1998.

  11. [57]  Molenberghs G., Beunckens C., Sotto C., and Kenward M. G. Every missing not at random model has got a missing at random counterpart with equal fit. Journal of the Royal Statistical Society, Series B, 70(2):371–388, 2008.

  12. [58]  Molenberghs G. and Lesaffre E. Marginal modelling of correlated ordinal data using an n-way plackett distribution. Journal of the American Statistical Association, 78(1):139–144, 1994.

  13. [59]  Molenberghs G., Njagi E. N., Kenward M. G., and Verbeke G. Enriched-data problems and essential non-identifiability. International Journal of Statistics in Medical Research, 1(1):16–44, 2012.

  1. [60]  Molenberghs G. and Verbeke G. Models for discrete longitudinal data. Springer, New York, 2005.

  2. [61]  Molenberghs G., Verbeke G., Efendi A., Braekers R., and Dem ́etrio C. G. B. A com- bined gamma frailty and normal random-effects model for repeated, overdispersed time-to-event data. Statistical Methods in Medical Research, 0(0):1–19, 2014.

  3. [62]  Molenberghs G., Verbeke G., and Dem ́etrio C. G. B. An extended random-effects approach to modeling repeated, overdispersed count data. Lifetime Data Analysis, 13(4):513–531, 2007.

  4. [63]  Molenberghs G., Verbeke G., Dem ́etrio C. G. B., and Vieira A. M. C. A family of generalized linear models for repeated measures with normal and conjugate random effects. Statistical Science, 25(3):325–347, 2010.

  5. [64]  Molenberghs G. and Kenward M. G. Missing data in clinical studies. John Wiley & Sons, Inc, 2007.

  6. [65]  Smith G. Statistical reasoning (3rd ed.). Allyn and Bacon, Boston, 1991.

  7. [66]  Verbeke G. and Lesaffre E. A linear mixed-effects model with heterogeneity in the random-effects population. Journal of the American Statistical Association, 91(433):217–221, 1996.

  8. [67]  Verbeke G. and Molenberghs G. Linear mixed models for longitudinal data. Springer, New York, 2000.

  9. [68]  Verbeke G. and Molenberghs G. Arbitrariness of models for augmented and coarse data, with emphasis on incomplete-data and random-effects models. Statistical Modelling, 10(4):391–419, 2010.

  10. [69]  Verbeke G. and Molenberghs G. The gradient function as an exploratory goodness- of-fit assessment of the random-effects distribution in mixed models. Biostatistics, 1(14):477–490, 2013.

  11. [70]  Verbeke G., Molenberghs G., and Rizopoulos D. Random effects models for longi- tudinal data. Longitudinal Research with Latent Variables, van Montfort, K., Oud, H., & Satorra, A.(Eds.), pages 37–96 (Chapter 2), 2004.

  12. [71]  Verbeke G., Molenberghs G., Thijs H., Lesaffre E., and Kenward M. G. Sensitivity analysis for non-random dropout: A local influence approach. Biometrics, 57(1):7– 14, 2001.

  13. [72]  Schwarz G. E. Estimating the dimension of a model. The Annals of Statistics, 6(2):461–464, 1978.

  14. [73]  Box G. E. P. and Tiao G. C. Bayesian inference in statistical analysis. John Wiley & Sons, Inc, New York, 1992.

  15. [74]  Fitzmaurice G. M., Davidian M., Molenberghs G., and Verbeke G. Longitudinal Data Analysis. Handbooks of Modern Statistical Methods, Chapman & Hall/CRC, New York, 2009.

  1. [75]  M. Galea, G. A. Paula, and H. Bolfarine. Local influence in elliptical linear regression models. The Statistician, 46(1):71–79, 1997.

  2. [76]  Akaike H. A new look at the statistical model identification. IEEE Transactions on Automatic Control, 19(6):716–723, 1974.

  3. [77]  Geys H., Molenberghs G., and Lipsitz S. R. A note on the comparison of pseudo- likelihood and generalized estimating equations for marginal odds ratio models. Journal of Statistical Computation and Simulation, 62(1–2):45–72, 1998.

  4. [78]  Joe H. and Lee Y. On weighting of bivariate margins in pairwise likelihood. Journal of Multivariate Analysis, 100(4):670–685, 2008.

  5. [79]  Tao H., Palta M., Yandell B. S., and Newton M. A. An estimation method for the semiparametric mixed effects model. Biometrics, 55(1):102–110, 1999.

  6. [80]  Van Oyen H. and Tafforeau J. Health interview surveys. Arch Public Health, 52(1):79–82, 1994.

  7. [81]  Van Oyen H., Tafforeau J., Hermans H., Quataert P., E. Schiettecatte, Lebrun L., and Belamer L. The belgian health interview survey. Arch Public Health, 55(1):1–13, 1997.

  8. [82]  Zhu H. T. and Lee S. Y. Local influence for incomplete-data models. Journal of the Royal Statistical Society. Series B, 63(1):111–126, 2001.

  9. [83]  Hammami I., Garcia A., and Nuel G. Evidence for overdispersion in the distribution of malaria parasites and leukocytes in thick blood smears. Malaria Journal, 12(398), 2013.

  10. [84]  Myung I. J. Tutorial on maximum likelihood estimation. Journal of mathematical Psychology, 47(1):90–100, 2002.

  11. [85]  Berger J. The case for objective bayesian analysis. Bayesian Analysis, 1(3):385–402, 2006.

  12. [86]  Chen J., Zhang D., and Davidian M. A monte carlo em algorithm for general- ized linear mixed models with flexible random effects distribution. Biostatistics, 3(3):347–360, 2002.

  13. [87]  Engel J. Models for response data showing extra-poisson variation. Statistica Neer- landica, 38(3):159–167, 1984.

  14. [88]  Hinde J. and Dem ́etrio C. G. B. Overdispersion: Models and estimation. Compu- tational Statistics and Data Analysis, 27(2):151–170, 1998a.

  15. [89]  Hinde J. and Dem ́etrio C. G. B. Overdispersion: Models and estimation. XIII Sinape, Sa ̃o Paulo, 1998b.

  16. [90]  Rasbash J., Steele F., Browne W. J., and Goldstein H. A user’s guide to MLwiN. Centre for Multilevel Modelling, University of Bristol, Bristol, 2014.

  1. [91]  Zhang J. and Heitjan D. F. Impact of nonignorable coarsening on bayesian inference. Biostatistics, 8(4)(1):722–743, 2007.

  2. [92]  Nelder J. A. and Wedderburn R. W. M. Generalized linear models. Journal of the Royal Statistical Society (Series A), 135(3):370–384, 1972.

  3. [93]  Pinheiro J. C. and Bates D. M. Mixed-effects models in S and S-PLUS. Statistics and Computing Series, Springer-Verlag, New York, 2000.

  4. [94]  Jansen J. F., Stambuk H. E., Koutcher J. A., and Shukla-Dave A. Non-gaussian analysis of diffusion-weighted mr imaging in head and neck squamous cell carcinoma: A feasibility study. American Journal of Neuroradiology, 31(4):741–748, 2010.

  5. [95]  Lawless J. F. Negative binomial and mixed poisson regression. Canadian Journal of Statistics, 15(3):209–225, 1987.

  6. [96]  Booth J. G., Casella G., Friedl H., and Hobert J. P. Negative binomial loglinear mixed models. Statistical Modelling, 3(3):179–181, 2003.

  7. [97]  Skellam J. G. A probability distribution derived from the binomial distribution by regarding the probability of success as variable between the sets of trials. Journal of the Royal Statistical Society. Series B (Methodological), 10(2):257–261, 1948.

  8. [98]  Faraway J. J. Extending the linear model with R: Generalized linear, mixed effects and nonparametric regression models. Chapman & Hall/CRC, Boca Raton, 2006.

  9. [99]  Lambrechts K. Information-accumulation theory of speeded categorization. Psy- chological Review, 107(2):227–260, 2000.

  10. [100]  Van Steen K., Molenberghs G., Verbeke G., and Thijs H. A local influence approach to sensitivity analysis of incomplete longitudinal ordinal data. Statistical Modelling, 1(2)(1):125–142, 2001.

  11. [101]  Manton K. G., Woodbury M. A., and Stallard E. A variance components approach to categorical data models with heterogenous cell populations: Analysis of spatial gradients in lung cancer mortality rates in north carolina counties. Biometrics, 37(2):259–269, 1981.

  12. [102]  Liang K. Y. and Zeger S. L. Longitudinal data analysis using generalized linear models. Biometrika, 73(1):13–22, 1986.

  13. [103]  Duchateau L. and Jassen P. The frailty model. Springer, New York, 2007.

  14. [104]  Magder L. S. and Zeger S. L. A smooth nonparametric estimate of a mixing distri- bution using mixtures of gaussians. Journal of the American Statistical Association, 91(435):1141–1151, 1996.

  15. [105]  Aerts M., Claeskens G., Hens N., and Molenberghs G. Local multiple imputation. Biometrika, 89(2):375–388, 2002.

  16. [106]  Aregay M., Shkedy Z., and Molenberghs G. A hierarchical bayesian overdispersion models for non-gaussian repeated measurement data. Computational Statistics and Data Analysis, Submitted, 2013.

  1. [107]  Aregay M., Shkedy Z., and Molenberghs G. A hierarchical bayesian approach for analysis of longitudinal count data with overdispersion parameters: A simulation study. Computational Statistics and Data Analysis, 57(1):233–245, 2013a.

  2. [108]  Davidian M. and Gallant A. R. The nonlinear mixed effects model with a smooth random effects density. Biometrika, 80(3):475–488, 1993.

  3. [109]  De Backer M., De Keyser P., De Vroey C., and E. Lesaffre. A 12-week treat- ment for dermatophyte toe onychomycosis: terbinafine 250mg/day vs. itracona- zole 200mg/daya double-blind comparative trial. British Journal of Dermatology, 134(46)(38):16–17, 1996.

  4. [110]  Evans M. and Swartz T. Methods for approximating integrals in statistics with special emphasis on bayesian integration problems. Statistical Science, 10(3):254– 272, 1995.

  5. [111]  Haker M., Bohme M., Martinetz T., and Barth E. Geometric invariants for facial feature tracking with 3d tof cameras. International Symposium on Signals, Circuits and Systems, 1(1):1–4, 2007.

  6. [112]  Griswold M. E. and Zeger S. L. On marginalized multilevel models and their com- putation. John Hopkins Bloomberg School of Public Health, 99(1):319–331, 2004.

  7. [113]  Kenward M. G., Goetghebeur E. J. T., and Molenberghs G. Sensitivity analysis for incomplete categorical data. Statistical Modelling, 1(1):31–48, 2001.

  8. [114]  Kenward M. G., Goetghebeur E. J. T., and Molenberghs G. Sensitivity analysis for incomplete categorical data. Statistical modelling, 1(1):31–48, 2001.

  9. [115]  Ouwens M. J. N. M., Tan F. E. S., and Berger M. P. F. Local influence to de- tect influential data structures for generalized linear mixed models. Biometrics, 57(4):1166–1172, 2001.

  10. [116]  Breslow N. E. Extra-poisson variation in log-linear models. Journal of the Royal Statistical Society, Series C (Applied Statistics), 33(1):38–44, 1984.

  11. [117]  Breslow N. E. Tests of hypotheses in overdispersed poisson regression and other quasi-likelihood models. Journal of the American Statistical Association, 85(410):565–571, 1990.

  12. [118]  Breslow N. E. and Clayton D.G. Approximate inference in generalized linear mixed models. Journal of the American Statistical Association, 88(412):9–25, 1993.

  13. [119]  Breslow N. E. and Lin X. Bias correction in generalized linear mixed models with a single component of dispersion. Biometrika, 82(1):81–91, 1995.

  14. [120]  Laird N. M. and Ware J. H. Random effects models for longitudinal data. Biomet- rics, 38(4):963–974, 1982.

  15. [121]  McCullagh P. and Nelder J. Generalized linear models (2nd ed.). Chapman & Hall/CRC, Boca Raton, 1989.

  1. [122]  Thall P. F. and Vail S. C. Some covariance models for longitudinal count data with overdispersion. Biometrics, 46(3):657–671, 1990.

  2. [123]  Davis P. J. and Rabinowitz P. Methods of numerical integration (2nd ed.). Academic Press, Dover, 1984.

  3. [124]  Diggle P. J., Heagerty P. J., Liang K. Y., and Zeger S. L. Analysis of Longitudinal Data. Oxford University Press, Oxford, 2002.

  4. [125]  Heagerty P. J. Marginally specified logistic-normal models for longitudinal binary data. Biometrics, 55(3):688–698, 1999.

  5. [126]  Heagerty P. J. and Zeger S. L. Marginalized multilevel models and likelihood infer- ence (with comments and a rejoinder by the authors). Statistical Science, 15(1):1–26, 2000.

  6. [127]  Christensen R. Principals of statistical inference. Journal of the American Statistical Association, 103(484):1719–1723, 2008.

  7. [128]  Ecochard R. and Clayton D. J. Fitting complex random effect models with stan- dard software using data augmentation: Application to a study of male and female fecundability. Statistical Modelling,, 1(4):319–331, 2002.

  8. [129]  Henderson R., Diggle P., and Dobson A. Joint modeling of longitudinal measure- ments and event time data. Biostatistics, 1(4):465–480, 2000.

  9. [130]  Schall R. Estimation in generalized linear models with random effects. Biometrika, 78(4):719–727, 1991.

  10. [131]  Swinburne R. Bayess theorem. Oxford University Press, Oxford, 2002.

  11. [132]  Willink R. Normal moments and hermite polynomials. Statistics and Probability

    Letters, 73(3):271–275, 2005.

  12. [133]  Wolfinger R. and O’Connell M. Generalized linear mixed models: a pseudo- likelihood approach. Journal of Statistical Computation and Simulation, 48(3):233– 243, 1993.

  13. [134]  Littell R. C., Stroup G. A., Wolfinger W. W., and Schabenberger O. SAS for mixed models (2nd ed.). SAS Institute Inc, Cary, 2006.

  14. [135]  Cook R. D. Assessment of local influence. Journal of the Royal Statistical Society, Series B, 48(2):133–169, 1986.

  15. [136]  Wolfinger R. D. and Chang M. Comparing the SAS GLM and MIXED procedures for repeated measures. SAS Institute Inc, Boca Raton, 1998.

  16. [137]  Wolfinger R. D. and Lin X. Two taylor-series approximation methods for nonlinear mixed models. Computational Statistics & Data Analysis archive, 25(4):465–490, 1997.

  17. [138]  Bahadur R. R. A representation of the joint distribution of responses to n dichoto- mous items. Studies in item analysis and prediction, 1(1):158–168, 1961.

  1. [139]  Wilcox R. R. A review of the beta-binomial model and its extensions. Journal of Educational Statistics, 6(1):3–32, 1981.

  2. [140]  Wedderburn R. W. M. Quasi-likelihood functions, generalized linear models, and the gauss-newton method. Biometrika, 61(3):439–447, 1974.

  3. [141]  Chib S. and Greenberg E. Understanding the metropolis-hastings algorithm. The American Statistician, 49(4):327–335, 1995.

  4. [142]  Fieuws S. and Verbeke G. Joint modelling of multivariate longitudinal profiles: pitfalls of the random-effects approach. Statistics in Medicine, 23(20):3093–3104, 2004.

  5. [143]  Geman S. and Geman D. Stochastic relaxation, gibbs distributions, and the bayesian restoration of images. IEEE Transactions on Pattern Analysis and Machine Intel- ligence, 6(6):721–741, 1984.

  6. [144]  Iddi S. and Molenberghs G. A combined overdispersed and marginalized multilevel model. Computational Statistics and Data Analysis, 56(6):1944–1951, 2012.

  7. [145]  Iddi S. and Molenberghs G. A joint marginalized multilevel model for longitu- dinal outcomes. 27th International Workshop on Statistical Modelling (Vol. 1), 39(11):165–170, 2012.

  8. [146]  Iddi S., Molenberghs G., Aregay M., and Kalema G. Empirical bayes estimates for correlated hierarchical data with overdispersion. Pharmaceutical Statistics, 13(5):316–326, 2014.

  9. [147]  le Cessie S. and van Houwelingen J. C. A goodness-of-fit test for binary regression models, based on smoothing methods. Biometrics, 47(4):1267–1282, 1991.

  10. [148]  Liu S. On local influence in elliptical linear regression models. Statistical Papers, 41(1):211–224, 2000.

  11. [149]  Liu S. Local influence in multivariate elliptical linear regression models. Linear Algebra and its Applications, 354(1–3):159–174, 2002.

  12. [150]  Cho S. J. and Rabe-Hesketh S. Alternating imputation posterior estimation of models with crossed random effects. Computational Statistics and Data Analysis, 55(1):12–25, 2011.

  13. [151]  Zeger S. L. and Liang K. Y. An overview of methods for the analysis of longitudinal data. Statistics in Medicine, 11(14–15):1825–1839, 1992.

  14. [152]  Zeger S. L., Liang K. Y., and Albert P. S. Models for longitudinal data: A gener- alized estimating equation approach. Biometrics, 44(4):1049–1060, 1988.

  15. [153]  Stigler S. M. The epic story of maximum likelihood. Statistical Science, 22(4):598– 620, 2007.

  16. [154]  Paul S. R., Plackett R. L., and Wedderburn R. W. M. Inference sensitivity for poisson mixtures. Biometrika, 65(3):591–602, 1978.

  1. [155]  Raudenbush S. W. Marginalized multilevel models and likelihood inference: Comments. Statistical Science, 15(1):22–24, 2000.

  2. [156]  Raudenbush S. W., Yang M. L., and Yosef M. Maximum likelihood for general- ized linear models with nested random effects via high-order, multivariate laplace approximation. Journal of Computational and Graphical Statistics, 9(1):141–157, 2000.

  3. [157]  Rakhmawati T., Molenberghs G., Verbeke G., and C. Faes. Local influence diagnos- tics for generalized linear mixed models with overdispersion. Statistical Modelling, 2014.

  4. [158]  Mwangi T. W., Fegan G., Williams T. N., Kinyanjui S.M., Snow R. W., and Marsh K. Evidence for over-dispersion in the distribution of clinical malaria episodes in children. Plos One, 3(5):21–96, 2014.

  5. [159]  Rakhmawati T. W., Molenberghs G., Verbeke G., and Faes C. Local influence diag- nostics for generalized linear mixed models with overdispersion. Not been published yet, 2014.

  6. [160]  Gardner W., William M., Mulvey E. P., and Shaw E. C. Regression analyses of counts and rates: Poisson, overdispersed poisson, and negative binomial models. Psychological Bulletin, 118(3):392–404, 1995.

  7. [161]  Shih W. J. Problems in dealing with missing data and informative censoring in clinical trials. Curr Control Trials Cardiovasc Med., 3(1)(4), 2002.

  8. [162]  Hastings W. K. Monte carlo sampling methods using markov chains and their applications. Biometrika, 57(1):97–109, 1970.

  9. [163]  Lin X. Variance component testing in generalised linear models with random effects. Biometrika, 84(2):309–326, 1997.

  10. [164]  Lee Y., Nelder J. A., and Pawitan Y. Generalized linear models with random effects: Unified analysis via H-likelihood. Chapman & Hall/CRC, Boca Raton, 2006.

  11. [165]  Tseng Y. K., Hsieh F., and Wang J. L. Joint modelling of accelerated failure time and longitudinal data. Biometrika, 92(3):587–603, 2005. 

 

Universiteit of Hogeschool
KU Leuven
Thesis jaar
2015
Thema('s)
Geneeskunde,
Informatica, kennistechnologie en ICT
Kernwoorden
Statistiek,
Gezondheidszorg,
gezondheid,
farmaceutica,
astma