Abstract
A class of estimators is proposed for the difference of means when sampling from a bivariate normal distribution with means μ1 and μ2, variances σ21 and σ22, and correlation coefficient p, where some observations on either of the variables are missing. The new estimator from this class is used to obtain some test statistics for testing the equality of means. Some additional test statistics are also proposed and the empirical powers of all statistics are computed for different values of σ21, σ22, and p. These computations support the use of some of the new test statistics.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 275-289 |
| Number of pages | 15 |
| Journal | Journal of Statistical Computation and Simulation |
| Volume | 19 |
| Issue number | 4 |
| DOIs | |
| State | Published - Jan 1984 |
All Science Journal Classification (ASJC) codes
- Statistics and Probability
- Modeling and Simulation
- Statistics, Probability and Uncertainty
- Applied Mathematics
Keywords
- Combination of independent tests
- Fisher's method
- empirical size and power
- equality of means
- incomplete data
- linear combination of independent variates
- paired t test
- unbiased estimator