Regression Estimation for Longitudinal Data with Nonignorable Intermittent Nonresponse and Dropout

Abstract

We mainly focus on regression estimation in a longitudinal study with nonignorable intermittent nonresponse and dropout. To handle the identifiability issue, we take a time-independent covariate as nonresponse instrument which is independent of nonresponse propensity conditioned on other covariates and responses to ensure the identifiability of nonresponse propensity. The nonresponse propensity is assumed to be a parametric model, and the corresponding parameters are estimated by using the generalized method of moments approach. Then the marginal response means are estimated by inverse probability weighting method. Furthermore, to improve the robustness of estimators, we derive an augmented inverse probability weighting estimator which is shown to be consistent and asymptotically normally distributed. Simulation studies and a real-data analysis show that the proposed approach yields highly efficient estimators.

Keywords

Dropout / Generalized method of moments / Inverse probability weighting / Intermittent nonresponse / Longitudinal data

References

[1] Ai, C., Linton, O., Zhang, Z.: A simple and efficient estimation method for models with nonignorable missing data. Statistica Sinica, preprint. (2018). https://doi.org/10.5705/ss.202018.0107

[2] Diggle PJ. The analysis of longitudinal data. J. Am. Stat. Assoc.. 2002, 90 1231-1232

[3] Fang F, Shao J. Model selection with nonignorable nonresponse. Biometrika. 2016, 103 861-874

[4] Fitzmaurice GM, Molenberghs G, Lipsitz SR. Regression models for longitudinal binary responses with informative dropouts. J. Roy. Stat. Soc. B. 1995, 57 691-704

[5] Han PS, Song PXK, Wang L. Achieving semiparametric efficiency bound in longitudinal data analysis with dropouts. J. Multivar. Anal.. 2015, 135 59-70

[6] Hansen L. Large sample properties of generalized method of moments estimators. Econometrica. 1982, 50 1029-1054

[7] Henry, K., Erice, A., Tierney, C., Balfour, H.H.J., Fischl, M.A., Kmack, A., Liou, S.H., Kenton, A., Hirsch, M.S., Phair, J., Martinez, A., Kahn, J.O. and for the AIDS Clinical Trial Group 193A Study Team: A randomized, controlled, double-blind study comparing the survival benefit of four different reverse transcriptase inhibitor therapies (three-drug, two-drug, and alternating drug) for the treatment of advanced AIDS. Journal of Acquired Immune Deficiency Syndromes and Human Retrovirology 19, 339–349 (1998)

[8] Kim JK, Yu CL. A semiparametric estimation of mean functionals with nonignorable missing data. J Am Stat Assoc. 2011, 106 157-165

[9] Little RJA, Rubin DB. Statistical Analysis with MissingData. 2002 2 New York: Wiley

[10] Miao W, Tchetgen E. On varieties of doubly robust estimators under missingness not at random with a shadow variable. Biometrika. 2016, 103 475-482

[11] Morikawa K, Kim JK, Kano Y. Semiparametric maximum likelihood estimation with data missing not at random. Can. J. Stat.. 2017, 45 393-409

[12] Newey W, Mcfadden D. Large Sample Estimation and Hypothesis Testing. 1994 New York: Springer

[13] Robins, et al.: Estimation of regression coefficients when some regressors are not always observed. J. Am. Stat. Assoc. 89: 846–866 (1994)

[14] Robins JM, Ritov Y. Toward a curse of dimensionality appropriate (CODA) asymptotic theory for semi-parametric models. Stat. Med.. 1997, 16 285-319

[15] Seaman SR, Farewell D, White IR. Linear increments with non-monotone missing data and measurement error. Scand. J. Stat.. 2016, 43 996-1018

[16] Shao J, Wang L. Semiparametric inverse propensity weighting for nonignorable missing data. Biometrika. 2016, 103 175-187

[17] Tsonaka R, Rizopoulos D, Verbeke G, Lesaffre E. Nonignorable models for intermittently missing categorical longitudinal responses. Biometrics. 2010, 66 834-844

[18] Vansteelandt S, Rotnitzky A, Robins J. Estimation of regression models for the mean of repeated outcomes under nonignorable nonmonotone nonresponse. Biometrika. 2007, 94 841-860

[19] Wang S, Shao J, Kim JK. An instrumental variable approach for identifcation and estimation with nonignorable nonresponse. Stat. Sin.. 2014, 24 1097-1116

[20] Wang, L., Shao, J., Fang, F.: Propensity model selection with nonignorable nonresponse and instrument variable. Stat. Sinica (2018). https://doi.org/10.5705/ss.202019.0025

[21] Wang L, Qi CC, Shao J. Model-assisted regression estimators for longitudinal data with nonignorable dropout. Int. Stat. Rev.. 2019, 87 S1 S121-S138

[22] Xu J, Shao J, Palta M, Wang L. Imputation for longitudinal data with last-value-dependent non-monotone missing values. Surv. Methodol.. 2008, 34 153-162

[23] Zhao J, Shao J. Semiparametric pseudo likelihoods in generalized linear models with nonignorable missing data. J. Am. Stat. Assoc.. 2015, 110 1577-1590

[24] Zhao P, Tang N, Qu A, Jiang D. Semiparametric estimating equations inference with nonignorable missing data. Stat. Sin.. 2017, 27 89-113

[25] Zhao P, Wang L, Shao J. Analysis of longitudinal data under nonignorable nonmonotone nonresponse. Stat. Interface. 2018, 11 265-279

[26] Zhou M, Kim JK. An efficient method of estimation for longitudinal surveys with monotone missing data. Biometrika. 2012, 99 631-648

Funding

Key Research and Development Plan(2016YFC0800100)

National Natural Science Foundation of China(11671374)

National Natural Science Foundation of China(71631006)