Abstract
We discuss the problem of performing inference on a causal effect of interest, such as an intention-to-treat effect, in the context of longitudinal clinical trials with informatively missing data. Addressing this problem requires the modeling of infinite-dimensional nuisance parameters; modeling these nuisance parameters poorly can result in substantial bias in the original estimation problem. Additionally, the presence of informative (nonignorable) missingness results in effects of interest being unidentified in the absence of strong, unverifiable, assumptions. We argue that Bayesian nonparametric methods are natural in this setting because they (1) allow for flexible modeling and (2) allow for uncertainty in untestable assumptions to be taken into account through the use of informative priors elicited from subject matter experts. We further argue that a sensitivity analysis to assess the impact of unverifiable assumptions is essential. Flexible Bayesian approaches which incorporate the longitudinal structure of the data are presented in the context of categorical and continuous outcomes, and strategies for sensitivity analysis are discussed in both cases. The methods are illustrated on data from a clinical trial designed to assess the efficacy of treatments for acute Schizophrenia.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Birmingham, J., Rotnitzky, A., and Fitzmaurice, G. M. (2003). Pattern-mixture and selection models for analysing longitudinal data with monotone missing patterns. Journal of the Royal Statistical Society, Series B., 65, 275–297.
Creemers, A., Hens, N., Aerts, M., Molenberghs, G., Verbeke, G., and Kenward, M. G. (2010). A sensitivity analysis for shared-parameter models for incomplete longitudinal outcomes. Biometrical Journal, 52(1), 111–125.
Daniels, M., Wang, C., and Marcus, B. (2014). Fully Bayesian inference under ignorable missingness in the presence of auxiliary covariates. Biometrics, 70(1), 62–72.
Daniels, M. J. (1999). A prior for the variance in hierarchical models. Canadian Journal of Statistics, 27(3), 567–578.
Daniels, M. J. and Hogan, J. W. (2000). Reparameterizing the pattern mixture model for sensitivity analyses under informative dropout. Biometrics, 56(4), 1241–1248.
Daniels, M. J. and Hogan, J. W. (2008). Missing data in longitudinal studies: Strategies for Bayesian modeling and sensitivity analysis. CRC Press.
Daniels, M. J. and Pourahmadi, M. (2002). Bayesian analysis of covariance matrices and dynamic models for longitudinal data. Biometrika, 89(3), 553–566.
Daniels, M. J., Chatterjee, A. S., and Wang, C. (2012). Bayesian model selection for incomplete data using the posterior predictive distribution. Biometrics, 68(4), 1055–1063.
Diggle, P. and Kenward, M. G. (1994). Informative drop-out in longitudinal data analysis. Applied statistics, pages 49–93.
Dunson, D. B. (2006). Bayesian dynamic modeling of latent trait distributions. Biostatistics, 7(4), 551–568.
Dunson, D. B. (2007). Bayesian methods for latent trait modelling of longitudinal data. Statistical Methods in Medical Research, 16, 399–415.
Dunson, D. B. and Herring, A. H. (2006). Semiparametric Bayesian latent trajectory models. Technical report, ISDS Discussion Paper 16, Duke Univ., Durham, NC, USA.
Dunson, D. B. and Perreault, S. D. (2001). Factor analytic models of clustered multivariate data with informative censoring. Biometrics, 57(1), 302–308.
Fieuws, S. and Verbeke, G. (2006). Pairwise fitting of mixed models for the joint modeling of multivariate longitudinal profiles. Biometrics, 62(2), 424–431.
Gael, J. V., Teh, Y. W., and Ghahramani, Z. (2009). The infinite factorial hidden Markov model. In Advances in Neural Information Processing Systems, pages 1697–1704.
Gelman, A., Jakulin, A., Pittau, M. G., and Su, Y.-S. (2008). A weakly informative default prior distribution for logistic and other regression models. The Annals of Applied Statistics, pages 1360–1383.
Harel, O. and Schafer, J. L. (2009). Partial and latent ignorability in missing-data problems. Biometrika, 96(1), 37–50.
Heckman, J. J. (1979). Sample selection bias as a specification error. Econometrica: Journal of the Econometric Society, pages 153–161.
Henderson, R., Diggle, P., and Dobson, A. (2000). Joint modelling of longitudinal measurements and event time data. Biostatistics, 1(4), 465–480.
Hogan, J. W. and Laird, N. M. (1997). Mixture models for the joint distribution of repeated measures and event times. Statistics in medicine, 16(3), 239–257.
Hogan, J. W., Daniels, M. J., and Hu, L. (2014). A bayesian perspective on assessing sensitivity to assumptions about unobserved data. In G. Molenberghs, G. Fitzmaurice, M. G. Kenward, A. Tsiatis, and G. Verbeke, editors, Handbook of Missing Data Methodology. CRC Press.
Johnson, V. E. and Albert, J. H. (1999). Ordinal Data Modeling. Statistics for Social Science and Public Policy. New York: Springer-Verlag.
Kenward, M., Molenberghs, G., and Thijs, H. (2003). Pattern-mixture models with proper time dependence. Biometrika, 90, 53–71.
Kim, C., Daniels, M. J., and Roy, J. A. (2015). A framework for Bayesian nonparametric inference for causal effects of mediation. Technical Report.
Kleinman, K. P. and Ibrahim, J. G. (1998). A semiparametric Bayesian approach to the random effects model. Biometrics, pages 921–938.
Kottas, A., Müller, P., and Quintana, F. (2005). Nonparametric Bayesian modeling for multivariate ordinal data. Journal of Computational and Graphical Statistics, 14(3), 610–625.
Linero, A. R. (2015a). Bayesian nonparametric analysis of longitudinal studies in the presence of informative missingness. Technical Report.
Linero, A. R. (2015b). Nonparametric Bayes: Inference Under Nonignorable Missingness and Model Selection. Ph.D. thesis, University of Florida.
Linero, A. R. and Daniels, M. J. (2015). A flexible Bayesian approach to monotone missing data in longitudinal studies with nonignorable missingness with application to an acute schizophrenia clinical trial. Journal of the American Statistical Association, in press.
Little, R. J. A. (1993). Pattern-mixture models for multivariate incomplete data. Journal of the American Statistical Association, 88(421), 125–134.
Little, R. J. A. (1994). A class of pattern-mixture models for normal incomplete data. Biometrika, 81(3), 471–483.
Little, R. J. A. and Rubin, D. B. (1986). Statistical analysis with missing data. John Wiley & Sons.
Manski, C. F. (2009). Identification for prediction and decision. Harvard University Press.
Meng, X. L. (1994). Multiple-imputation inferences with uncongenial sources of input. Statistical Science, pages 538–558.
Molenberghs, G., Michiels, B., Kenward, M. G., and Diggle, P. J. (1998). Monotone missing data and pattern-mixture models. Statistica Neerlandica, 52, 153–161.
Molenberghs, G., Fitzmaurice, G., Kenward, M. G., Tsiatis, A., and Verbeke, G. (2014). Handbook of Missing Data Methodology. CRC Press.
National Research Council (2010). The Prevention and Treatment of Missing Data in Clinical Trials. The National Academies Press.
Njagi, E. N., Molenberghs, G., Kenward, M. G., Verbeke, G., and Rizopoulos, D. (2014). A characterization of missingness at random in a generalized shared-parameter joint modeling framework for longitudinal and time-to-event data, and sensitivity analysis. Biometrical Journal, 56(6), 1001–1015.
Pati, D., Reich, B. J., and Dunson, D. B. (2011). Bayesian geostatistical modelling with informative sampling locations. Biometrika, 98(1), 35–48.
Ren, L., Dunson, D. B., and Carin, L. (2008). The dynamic hierarchical Dirichlet process. In Proceedings of the 25th international conference on Machine learning, pages 824–831. ACM.
Robins, J. (1989). The control of confounding by intermediate variables. Statistics in medicine, 8(6), 679–701.
Robins, J. M. (1986). A new approach to causal inference in mortality studies with sustained exposure periods – application to control of the healthy worker survivor effect. Math Modeling, 7, 1393–1512.
Robins, J. M. (1997). Non-response models for the analysis of non-monotone non-ignorable missing data. Statistics in Medicine, 16(1), 21–37.
Robins, J. M. and Ritov, Y. (1997). Toward a curse of dimensionality appropriate(CODA) asymptotic theory for semi-parametric models. Statistics in medicine, 16(3), 285–319.
Robins, J. M., Rotnitzky, A., and Scharfstein, D. O. (2000). Sensitivity analysis for selection bias and unmeasured confounding in missing data and causal inference models. In Statistical models in epidemiology, the environment, and clinical trials, pages 1–94. Springer.
Roy, J. (2003). Modeling longitudinal data with nonignorable dropouts using a latent dropout class model. Biometrics, 59(4), 829–836.
Rubin, D. (1976). Inference and missing data. Biometrika, 63, 581–592.
Rubin, D. B. (1987). Multiple Imputation for Nonresponse in Surveys. Wiley.
Scharfstein, D., McDermott, A., Olson, W., and Wiegand, F. (2014). Global sensitivity analysis for repeated measures studies with informative dropout: A fully parametric approach. Statistics in Biopharmaceutical Research, 6(4), 338–348.
Scharfstein, D. O., Rotnitzky, A., and Robins, J. M. (1999). Adjusting for nonignorable dropout using semiparametric nonresponse models. Journal of the American Statistical Association, 94, 1096–1146.
Scharfstein, D. O., Daniels, M. J., and Robins, J. M. (2003). Incorporating prior beliefs about selection bias into the analysis of randomized trials with missing outcomes. Biostatistics, 4(4), 495–512.
Si, Y. and Reiter, J. P. (2013). Nonparametric Bayesian multiple imputation for incomplete categorical variables in large-scale assessment surveys. Journal of Educational and Behavioral Statistics, 38(5), 499–521.
Teh, Y. W., Jordan, M. I., Beal, M. J., and Blei, D. M. (2006). Hierarchical Dirichlet processes. Journal of the American Statistical Association, 101(476).
Thijs, H., Molenberghs, G., Michiels, B., Verbeke, G., and Curran, D. (2002). Strategies to fit pattern-mixture models. Biostatistics, 3(2), 245–265.
Vansteelandt, S., Goetghebeur, E., Kenward, M., and Molenberghs, G. (2006). Ignorance and uncertainty regions as inferential tools in a sensitivity analysis. Statistica Sinica, 16, 953–979.
Vansteelandt, S., Rotnitzky, A., and Robins, J. (2007). Estimation of regression models for the mean of repeated outcomes under nonignorable nonmonotone nonresponse. Biometrika, 94(4), 841–860.
Wang, C., Danies, M. J., Scharfstein, D. O., and Land, S. (2010). A Bayesian shrinkage model for incomplete longitudinal binary data with application to the breast cancer prevention trial. Journal of the American Statistical Association, 105, 1333–1346.
Williamson, S., Orbanz, P., and Ghahramani, Z. (2010). Dependent Indian buffet processes. In International conference on artificial intelligence and statistics, pages 924–931.
Wu, M. C. and Carroll, R. J. (1988). Estimation and comparison of changes in the presence of informative right censoring by modeling the censoring process. Biometrics, pages 175–188.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Daniels, M.J., Linero, A.R. (2015). Bayesian Nonparametrics for Missing Data in Longitudinal Clinical Trials. In: Mitra, R., Müller, P. (eds) Nonparametric Bayesian Inference in Biostatistics. Frontiers in Probability and the Statistical Sciences. Springer, Cham. https://doi.org/10.1007/978-3-319-19518-6_21
Download citation
DOI: https://doi.org/10.1007/978-3-319-19518-6_21
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-19517-9
Online ISBN: 978-3-319-19518-6
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)