Main Article Content
Abstract
Estimation of parameters of the general linear model will pose problems in the presence of measurement errors with missing data. In some cases there will be gaps in the data or some observations may be completely missing. For example, in an agriculture experiment the observations from some plots may not be available. These situations necessitate the estimation of the missing observations. In these contexts some standard techniques for predicating the observations would be of much use. Considerable attention was paid by several researchers for this particular pattern of missing observations and a lot of literature appeared. In this paper an attempt has been made to provided an estimator of parameter vector in the presence of measurement errors and missing data. Extensive Monte Carlo study revealed that the new estimator is more efficient than OLE.