Nearly Best Conditional Linear Unbiased Estimation of the Mean and Standard Deviation of the Logistic Distribution.
AIR FORCE INST OF TECH WRIGHT-PATTERSON AFB OHIO SCHOOL OF ENGINEERING
Pagination or Media Count:
The method of Lagrangian multipliers is used to find nearly best, minimum-variance, linear, unbiased, conditional estimator coefficients for the mean and standard deviation of the logistic distribution using M-order statistics. Coefficients for conditional parameter estimation are developed for full and censored samples of size N 2140. The equations for the estimators are derived in detail. Two types of censoring are used single censoring from above and symmetrical censoring from each end. The results are presented in tables of coefficients for conditional estimation of the unknown parameter. It is shown how the tabled coefficients can be used for simultaneous estimation. Author
- Statistics and Probability