Abstract
A problem of testing of hypotheses on the mean vector of a multivariate normal distribution with unknown and positive definite covariance matrix is considered when a sample with missing observations from that population is available. Simple approximations to the distribution of the test statistic are derived and are used to compute the approximate percentage points. The accuracy of the approximate percentage points has been assessed by comparing them with some exact percentage points. The comparison shows that the approximate percentage points are in good agreement with the exact percentage points. The approximations to the test statistic for testing the hypothesis of equality of two mean vectors of two multivariate normal distributions are also obtained