TY - JOUR

T1 - Consistent estimators of the variance-covariance matrix of the gmanova model with missing data

AU - Mensah, Robert D.

AU - Elswick, R. K.

AU - Chinchilli, Vernon M.

PY - 1993/1/1

Y1 - 1993/1/1

N2 - A common problem in multivariate general linear models is partially missing response data. The simplest method of analysis in the presencea of missing data has been to delete all observations on any individual with any missing data (listwise deletion) and utilize a traditional complete data approach. However, this can result in a great loss of information, and perhaps inconsistencies in the estimation of the variancecovariance matrix. In the generalized multivariate analysis of variance (GMANOVA) model with missing data, Kleinbaum (1973) proposed an estimated generalized least squares approach. In order to apply this, however, a consistent estimate of the variance-covariance matrix is needed. Kleinbaum proposed an estimator which is unbiased and consistent, but it does not take advantage of the fact that the underlying model is GMANOVA and not MANOVA. Using the fact that the underlying model is GMANOVA we have constructed four other consistent estimators. A Monte Carlo simulation experiment is conducted to further examine how well these estimators compare to the estimator proposed by Kleinbaum.

AB - A common problem in multivariate general linear models is partially missing response data. The simplest method of analysis in the presencea of missing data has been to delete all observations on any individual with any missing data (listwise deletion) and utilize a traditional complete data approach. However, this can result in a great loss of information, and perhaps inconsistencies in the estimation of the variancecovariance matrix. In the generalized multivariate analysis of variance (GMANOVA) model with missing data, Kleinbaum (1973) proposed an estimated generalized least squares approach. In order to apply this, however, a consistent estimate of the variance-covariance matrix is needed. Kleinbaum proposed an estimator which is unbiased and consistent, but it does not take advantage of the fact that the underlying model is GMANOVA and not MANOVA. Using the fact that the underlying model is GMANOVA we have constructed four other consistent estimators. A Monte Carlo simulation experiment is conducted to further examine how well these estimators compare to the estimator proposed by Kleinbaum.

UR - http://www.scopus.com/inward/record.url?scp=0342992333&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0342992333&partnerID=8YFLogxK

U2 - 10.1080/03610929308831100

DO - 10.1080/03610929308831100

M3 - Article

AN - SCOPUS:0342992333

VL - 22

SP - 1495

EP - 1514

JO - Communications in Statistics - Theory and Methods

JF - Communications in Statistics - Theory and Methods

SN - 0361-0926

IS - 6

ER -