Research Article
An index of local sensitivity to nonignorable drop‐out in longitudinal modelling
Abstract
In longitudinal studies with potentially nonignorable drop‐out, one can assess the likely effect of the nonignorability in a sensitivity analysis. Troxel et al. proposed a general index of sensitivity to nonignorability, or ISNI, to measure sensitivity of key inferences in a neighbourhood of the ignorable, missing at random (MAR) model. They derived detailed formulas for ISNI in the special case of the generalized linear model with a potentially missing univariate outcome. In this paper, we extend the method to longitudinal modelling. We use a multivariate normal model for the outcomes and a regression model for the drop‐out process, allowing missingness probabilities to depend on an unobserved response. The computation is straightforward, and merely involves estimating a mixed‐effects model and a selection model for the drop‐out, together with some simple arithmetic calculations. We illustrate the method with three examples. Copyright © 2005 John Wiley & Sons, Ltd.
Citing Literature
Number of times cited according to CrossRef: 45
- Chengbo Yuan, Donald Hedeker, Robin Mermelstein, Hui Xie, A tractable method to account for high‐dimensional nonignorable missing data in intensive longitudinal data, Statistics in Medicine, 10.1002/sim.8560, 39, 20, (2589-2605), (2020).
- Zhihua Ma, Guanghui Chen, Bayesian joint analysis using a semiparametric latent variable model with non-ignorable missing covariates for CHNS data, Statistical Modelling, 10.1177/1471082X19896688, (1471082X1989668), (2020).
- Fariba Azizi, Samaneh Eftekhari Mahabadi, Elham Mosayebi Omshi, Bayesian sensitivity analysis to the non-ignorable missing cause of failure for hybrid censored competing risks data, Journal of Statistical Computation and Simulation, 10.1080/00949655.2020.1773464, (1-28), (2020).
- Samaneh Eftekhari Mahabadi, Second‐order local sensitivity to non‐ignorability in Bayesian inferences, Statistics in Medicine, 10.1002/sim.7829, 37, 25, (3616-3636), (2018).
- Alessandra Spagnoli, Maria Francesca Marino, Marco Alfò, A bidimensional finite mixture model for longitudinal data subject to dropout, Statistics in Medicine, 10.1002/sim.7698, 37, 20, (2998-3011), (2018).
- Andrea L. Cheville, Timothy Moynihan, Jeffrey R. Basford, John A. Nyman, Marty L. Tuma, Debra A. Macken, Terry Therneau, Daniel Satelel, Kurt Kroenke, The rationale, design, and methods of a randomized, controlled trial to evaluate the effectiveness of collaborative telecare in preserving function among patients with late stage cancer and hematologic conditions, Contemporary Clinical Trials, 10.1016/j.cct.2017.08.021, 64, (254-264), (2018).
- Hui Xie, Weihua Gao, Baodong Xing, Daniel F. Heitjan, Donald Hedeker, Chengbo Yuan, Measuring the Impact of Nonignorable Missingness Using the R Package isni, Computer Methods and Programs in Biomedicine, 10.1016/j.cmpb.2018.06.014, 164, (207-220), (2018).
- Daniel O Scharfstein, Aidan McDermott, Global sensitivity analysis of clinical trials with missing patient-reported outcomes, Statistical Methods in Medical Research, 10.1177/0962280218759565, (096228021875956), (2018).
- Peng Yin, Jian Q Shi, Simulation-based sensitivity analysis for non-ignorably missing data, Statistical Methods in Medical Research, 10.1177/0962280217722382, 28, 1, (289-308), (2017).
- Daniel F Heitjan, Commentary on Mason et al., Clinical Trials: Journal of the Society for Clinical Trials, 10.1177/1740774517711443, 14, 4, (368-369), (2017).
- Maria Francesca Marino, Nikos Tzavidis, Marco Alfò, Mixed hidden Markov quantile regression models for longitudinal data with possibly incomplete sequences, Statistical Methods in Medical Research, 10.1177/0962280216678433, 27, 7, (2231-2246), (2016).
- Weihua Gao, Donald Hedeker, Robin Mermelstein, Hui Xie, A scalable approach to measuring the impact of nonignorable nonresponse with an EMA application, Statistics in Medicine, 10.1002/sim.7078, 35, 30, (5579-5602), (2016).
- Samaneh Eftekhari Mahabadi, Mojtaba Ganjali, A Bayesian approach for sensitivity analysis of incomplete multivariate longitudinal data with potential nonrandom dropout, METRON, 10.1007/s40300-015-0063-6, 73, 3, (397-417), (2015).
- Daniel Scharfstein, Aidan McDermott, William Olson, Frank Wiegand, Global Sensitivity Analysis for Repeated Measures Studies With Informative Dropout: A Fully Parametric Approach, Statistics in Biopharmaceutical Research, 10.1080/19466315.2014.966920, 6, 4, (338-348), (2014).
- Hayley M. Belli, Andrea B. Troxel, The Protective Estimator: A Tool for Longitudinal Analysis with Missing Data, Wiley StatsRef: Statistics Reference Online, 10.1002/9781118445112, (1-8), (2014).
- Sara Viviani, Dimitris Rizopoulos, Marco Alfó, Local sensitivity to non-ignorability in joint models, Statistical Modelling: An International Journal, 10.1177/1471082X13504716, 14, 3, (205-228), (2014).
- Yuming Ning, Gail McAvay, Sarwat I. Chaudhry, Alice M. Arnold, Heather G. Allore, Results Differ by Applying Distinctive Multiple Imputation Approaches on the Longitudinal Cardiovascular Health Study Data, Experimental Aging Research, 10.1080/0361073X.2013.741968, 39, 1, (27-43), (2013).
- Fang Zhu, Gong Tang, An Index of Local Sensitivity to Nonignorability for a Pseudolikelihood Method, Communications in Statistics - Theory and Methods, 10.1080/03610926.2011.588367, 42, 6, (954-973), (2013).
- Chi-hong Tseng, Robert Elashoff, Ning Li, Gang Li, Longitudinal data analysis with non-ignorable missing data, Statistical Methods in Medical Research, 10.1177/0962280212448721, 25, 1, (205-220), (2012).
- Hui Xie, Yi Qian, Measuring the impact of nonignorability in panel data with non‐monotone nonresponse, Journal of Applied Econometrics, 10.1002/jae.1157, 27, 1, (129-159), (2012).
- S. Eftekhari Mahabadi, M. Ganjali, An index of local sensitivity to non-ignorability for parametric survival models with potential non-random missing covariate: an application to the SEER cancer registry data, Journal of Applied Statistics, 10.1080/02664763.2012.710196, 39, 11, (2327-2348), (2012).
- Hui Xie, Analyzing longitudinal clinical trial data with nonignorable missingness and unknown missingness reasons, Computational Statistics & Data Analysis, 10.1016/j.csda.2010.11.021, 56, 5, (1287-1300), (2012).
- Dimitris Rizopoulos, Bibliography, Joint Models for Longitudinal and Time-to-Event Data, 10.1201/b12208-12, (239-255), (2012).
- Andrea Troxel, Carol Moinpour, John Crowley, Antje Hoering, Design and Analysis of Quality-of-Life Data, Handbook of Statistics in Clinical Oncology, Third Edition, 10.1201/b11800, (339-368), (2012).
- N. A. Kaciroti, T. E. Raghunathan, J. M. G. Taylor, S. Julius, A Bayesian model for time-to-event data with informative censoring, Biostatistics, 10.1093/biostatistics/kxr048, 13, 2, (341-354), (2012).
- Leopoldo J Cabassa, Benjamin Druss, Yuanjia Wang, Roberto Lewis-Fernández, Collaborative planning approach to inform the implementation of a healthcare manager intervention for hispanics with serious mental illness: a study protocol, Implementation Science, 10.1186/1748-5908-6-80, 6, 1, (2011).
- Hui Xie, Adjusting for Nonignorable Missingness When Estimating Generalized Additive Models, Biometrical Journal, 10.1002/bimj.200900202, 52, 2, (186-200), (2010).
- Sarwat I. Chaudhry, Gail McAvay, Yuming Ning, Heather G. Allore, Anne B. Newman, Thomas M. Gill, Geriatric Impairments and Disability: The Cardiovascular Health Study, Journal of the American Geriatrics Society, 10.1111/j.1532-5415.2010.03022.x, 58, 9, (1686-1692), (2010).
- S. Eftekhari Mahabadi, M. Ganjali, An index of local sensitivity to non‐ignorability for multivariate longitudinal mixed data with potential non‐random dropout, Statistics in Medicine, 10.1002/sim.3948, 29, 17, (1779-1792), (2010).
- Sanjib Basu, Sourav Santra, A joint model for incomplete data in crossover trials, Journal of Statistical Planning and Inference, 10.1016/j.jspi.2010.03.006, 140, 10, (2839-2845), (2010).
- Peter Congdon, References, Applied Bayesian Hierarchical Methods, 10.1201/9781584887218, (495-500), (2010).
- Hui Xie, Bayesian inference from incomplete longitudinal data: A simple method to quantify sensitivity to nonignorable dropout, Statistics in Medicine, 10.1002/sim.3655, 28, 22, (2725-2747), (2009).
- Hua Yun Chen, Shasha Gao, Estimation of average treatment effect with incompletely observed longitudinal data: Application to a smoking cessation study, Statistics in Medicine, 10.1002/sim.3617, 28, 19, (2451-2472), (2009).
- Hui Xie, Daniel F. Heitjan, Local Sensitivity to Nonignorability: Dependence on the Assumed Dropout Mechanism, Statistics in Biopharmaceutical Research, 10.1198/sbr.2009.0028, 1, 3, (243-257), (2009).
- G. Cottrell, M. Cot, J.-Y. Mary, L’imputation multiple des données manquantes aléatoirement : concepts généraux et présentation d’une méthode Monte-Carlo, Revue d'Épidémiologie et de Santé Publique, 10.1016/j.respe.2009.04.011, 57, 5, (361-372), (2009).
- Niko A. Kaciroti, M. Anthony Schork, Trivellore Raghunathan, Stevo Julius, A Bayesian sensitivity model for intention‐to‐treat analysis on binary outcomes with dropouts, Statistics in Medicine, 10.1002/sim.3494, 28, 4, (572-585), (2008).
- Craig H. Mallinckrod†, Peter W. Lane, Dan Schnell, Yahong Peng, James P. Mancuso, Recommendations for the Primary Analysis of Continuous Endpoints in Longitudinal Clinical Trials, Drug Information Journal, 10.1177/009286150804200402, 42, 4, (303-319), (2008).
- Hui Xie, A local sensitivity analysis approach to longitudinal non‐Gaussian data with non‐ignorable dropout, Statistics in Medicine, 10.1002/sim.3117, 27, 16, (3155-3177), (2007).
- Sati Mazumdar, Gong Tang, Patricia R. Houck, Mary Amanda Dew, Amy E. Begley, John Scott, Benoit H. Mulsant, Charles F. Reynolds, Statistical analysis of longitudinal psychiatric data with dropouts, Journal of Psychiatric Research, 10.1016/j.jpsychires.2006.09.007, 41, 12, (1032-1041), (2007).
- Peter H. Van Ness, Terrence E. Murphy, Katy L.B. Araujo, Margaret A. Pisani, Heather G. Allore, The use of missingness screens in clinical epidemiologic research has implications for regression modeling, Journal of Clinical Epidemiology, 10.1016/j.jclinepi.2007.03.006, 60, 12, (1239-1245), (2007).
- Jiameng Zhang, Daniel F. Heitjan, A Simple Local Sensitivity Analysis Tool for Nonignorable Coarsening: Application to Dependent Censoring, Biometrics, 10.1111/j.1541-0420.2006.00580.x, 62, 4, (1260-1268), (2006).
- R. J. O'Hara Hines, W. G. S. Hines, An index of local sensitivity to nonignorable drop‐out in longitudinal modelling by G. Ma, A. B. Troxel and D. F. Heitjan, Statistics in Medicine 2005; 24:2129–2150, Statistics in Medicine, 10.1002/sim.2527, 25, 18, (3217-3218), (2006).
- Ma Guoguang, Andrea B. Troxel, Daniel F. Heitjan, Authors' Reply, Statistics in Medicine, 10.1002/sim.2526, 25, 18, (3218-3220), (2006).
- Shuyi Shen, Caroline Beunckens, Craig Mallinckrodt, Geert Molenberghs, A Local Influence Sensitivity Analysis for Incomplete Longitudinal Depression Data, Journal of Biopharmaceutical Statistics, 10.1080/10543400600609510, 16, 3, (365-384), (2006).
- Daniel F. Heitjan, Samuel Kotz, Campbell B. Read, N. Balakrishnan, Brani Vidakovic, Norman L. Johnson, Ignorability, Encyclopedia of Statistical Sciences, 10.1002/0471667196, (1-4), (2004).
