© 1994 by Biometrika Trust
Articles |
A class of pattern-mixture models for normal incomplete data
Department of Biostatistics, University of Michigan Ann Arbor, Michigan 48109-2029, U.S.A.
Received for publication 1 June 1992.
Revision received 1 July 1993.
 |
Abstract |
|---|
Likelihood-based methods are developed for analyzing a random sample on two continuous variables when values of one of the variables are missing. Normal maximum likelihood estimates when values are missing completely at random were derived by Anderson (1957). They are also maximum likelihood providing the missing-data mechanism is ignorable, in Rubin's (1976) sense that the mechanism depends only on observed data. A new class of pattern-mixture models (Little, 1993) is described for the situation where missingness is assumed to depend on an arbitrary unspecified function of a linear combination of the two variables. Maximum likelihood for models in this class is straightforward, and yields the estimates of Anderson (1957) when missingness depends solely on the completely observed variable, and the estimates of Brown (1990) when missingness depends solely on the incompletely observed variable. Another choice of linear combination yields estimates from complete-case analysis. Large-sample and Bayesian methods are described for this model. The data do not supply information about the ratio of the coefficients of the linear combination that controls missingness. If this ratio is not well-determined based on prior knowledge, a prior distribution can be specified, and Bayesian inference is then readily accomplished. Alternatively, sensitivity of inferences can be displayed for a variety of choices of the ratio.
Key Words: Imputation • Maximum likelihood • Missing values • Monotone missing data • Multiple imputation • Nonrandom missing data • Nonresponse • Selection bias
CiteULike 
Connotea 
Del.icio.us What's this?
This article has been cited by other articles:
|
|
 |
|
  L. Su and J. W. Hogan Varying-coefficient models for longitudinal processes with continuous-time informative dropout Biostat., October 15, 2009; (2009) kxp040v1. [Abstract] [Full Text] [PDF]
|
|
|
|
 |
|
 A. Marques, P. Shaw, C. H. Schmid, A. Steere, R. F. Kaplan, A. Hassett, E. Shapiro, G. P. Wormser, B. A. Fallon, E. Petkova, et al. A RANDOMIZED, PLACEBO-CONTROLLED TRIAL OF REPEATED IV ANTIBIOTIC THERAPY FOR LYME ENCEPHALOPATHY PROLONGED LYME DISEASE TREATMENT: ENOUGH IS ENOUGH Neurology, January 27, 2009; 72(4): 383 - 386. [Full Text] [PDF]
|
|
|
|
 |
|
 M. G. Perri, M. C. Limacher, P. E. Durning, D. M. Janicke, L. D. Lutes, L. B. Bobroff, M. S. Dale, M. J. Daniels, T. A. Radcliff, and A. D. Martin Extended-Care Programs for Weight Management in Rural Communities: The Treatment of Obesity in Underserved Rural Settings (TOURS) Randomized Trial Arch Intern Med, November 24, 2008; 168(21): 2347 - 2354. [Abstract] [Full Text] [PDF]
|
|
|
|
 |
|
 D. Cella, J. Z. Li, J. C. Cappelleri, A. Bushmakin, C. Charbonneau, S. T. Kim, I. Chen, and R. J. Motzer Quality of Life in Patients With Metastatic Renal Cell Carcinoma Treated With Sunitinib or Interferon Alfa: Results From a Phase III Randomized Trial J. Clin. Oncol., August 1, 2008; 26(22): 3763 - 3769. [Abstract] [Full Text] [PDF]
|
|
|
|
 |
|
 M. G Kenward and J. Carpenter Multiple imputation: current perspectives Statistical Methods in Medical Research, June 1, 2007; 16(3): 199 - 218. [Abstract] [PDF]
|
|
|
|
 |
|
 S Fielding, P M Fayers, J H Loge, M S Jordhoy, and S Kaasa Methods for handling missing data in palliative care research Palliative Medicine, December 1, 2006; 20(8): 791 - 798. [Abstract] [PDF]
|
|
|
|
|
|
D. O. Scharfstein, M. E. Halloran, H. Chu, and M. J. Daniels On estimation of vaccine efficacy using validation samples with selection bias Biostat., October 1, 2006; 7(4): 615 - 629. [Abstract] [Full Text] [PDF]
|
|
|
|
|
|
D. L Fairclough Patient reported outcomes as endpoints in medical research Statistical Methods in Medical Research, April 1, 2004; 13(2): 115 - 138. [Abstract] [PDF]
|
|
|
|
|
|
P. A. Ganz, C. M. Moinpour, D. K. Pauler, A. B. Kornblith, E. R. Gaynor, S. P. Balcerzak, G. S. Gatti, H. P. Erba, S. McCoy, O. W. Press, et al. Health Status and Quality of Life in Patients With Early-Stage Hodgkin's Disease Treated on Southwest Oncology Group Study 9133 J. Clin. Oncol., September 15, 2003; 21(18): 3512 - 3519. [Abstract] [Full Text] [PDF]
|
|
|
|
 |
|
 G. Molenberghs and G. Verbeke A review on linear mixed models for longitudinal data, possibly subject to dropout Statistical Modeling, December 1, 2001; 1(4): 235 - 269. [Abstract] [PDF]
|
|
|
|
|
|
K. van Steen, G. Molenberghs, G. Verbeke, and H. Thijs A local influence approach to sensitivity analysis of incomplete longitudinal ordinal data Statistical Modeling, July 1, 2001; 1(2): 125 - 142. [Abstract] [PDF]
|
|
|
|
|
|
M. G Kenward, E. J. Goetghebeur, and G. Molenberghs Sensitivity analysis for incomplete categorical data Statistical Modeling, April 1, 2001; 1(1): 31 - 48. [Abstract] [PDF]
|
|
|
|
 |
|
 F. Li, T. E. Duncan, E. Mcauley, P. Harmer, and K. Smolkowski A Didactic Example of Latent Curve Analysis Applicable to the Study of Aging J Aging Health, August 1, 2000; 12(3): 388 - 425. [Abstract] [PDF]
|
|
|
|
 |
|
 M. Ranson, N. Davidson, M. Nicolson, S. Falk, J. Carmichael, P. Lopez, H. Anderson, N. Gustafson, A. Jeynes, G. Gallant, et al. Randomized Trial of Paclitaxel Plus Supportive Care Versus Supportive Care for Patients With Advanced Non-Small-Cell Lung Cancer J Natl Cancer Inst, July 5, 2000; 92(13): 1074 - 1080. [Abstract] [Full Text] [PDF]
|
|
|
|
|
|
M G Kenward and G Molenberghs Parametric models for incomplete continuous and categorical longitudinal data Statistical Methods in Medical Research, February 1, 1999; 8(1): 51 - 83. [Abstract] [PDF]
|
|