An analysis of longitudinal data with nonignorable dropout using the truncated multivariate normal distribution

For a vector of multivariate normal when some elements, but not necessarily all, are truncated, we derive the moment generating function and obtain expressions for the first two moments involving the multivariate hazard gradient. To show one of many applications of these moments, we then extend the two-step estimation of censored regression models to longitudinal studies with nonignorable dropout, in the sense that the probability of dropout depends on unobserved, or missing, observations. With nonignorable dropout, direct maximization of the likelihood function can be computationally intensive or even infeasible. The two-step method in such cases can be an adequate substitute. In a set of simulation studies the developed two-step method and the maximum likelihood (ML) method are compared. It turns out that the proposed method preforms at least as well as the ML and provides a convenient alternative that can easily be implemented in standard software.

[1]  Samuel Kotz,et al.  A vector multivariate hazard rate , 1975 .

[2]  D. Rubin.  INFERENCE AND MISSING DATA , 1975 .

[3]  Dale J. Poirier,et al.  Partial observability in bivariate probit models , 1980 .

[4]  D. Rubin,et al.  Statistical Analysis with Missing Data , 1988 .

[5]  M. Kenward,et al.  Informative dropout in longitudinal data analysis (with discussion) , 1994 .

[6]  The multivariate hazard gradient and moments of the truncated multinormal distribution , 1992 .

[7]  Frank Bretz,et al.  Comparison of Methods for the Computation of Multivariate t Probabilities , 2002 .

[8]  Robert Tibshirani,et al.  Bootstrap Methods for Standard Errors, Confidence Intervals, and Other Measures of Statistical Accuracy , 1986 .

[9]  S. Lipsitz,et al.  Protective estimator for linear regression with nonignorably missing Gaussian outcomes , 2004 .

[10]  Lung-fei Lee,et al.  Asymptotic Covariance Matrices of Two-Stage Probit and Two-Stage Tobit Methods for Simultaneous Equations Models with Selectivity , 1980 .

[11]  A. Genz,et al.  Computation of Multivariate Normal and t Probabilities , 2009 .

[12]  J. Heckman.  Sample selection bias as a specification error , 1979 .

[13]  Alan,et al.  Comparison of Methods for the Computationof Multivariate Normal Probabilities , 1993 .

[14]  A. Genz.  Numerical Computation of Multivariate Normal Probabilities , 1992 .

[15]  Derrick S. Tracy,et al.  Recurrence relations for the moments of truncated multinormal distribution , 1976 .

[16]  M. Kenward.  Selection models for repeated measurements with non-random dropout: an illustration of sensitivity. , 1998, Statistics in medicine.

[17]  W. Greene,et al.  计量经济分析 = Econometric analysis , 2009 .