Premium
ESTIMATING THE PARAMETERS OF NORMAL AND LOGISTIC DISTRIBUTIONS FROM CENSORED SAMPLES 1
Author(s) -
Tiku M. L.
Publication year - 1968
Publication title -
australian journal of statistics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.434
H-Index - 41
eISSN - 1467-842X
pISSN - 0004-9581
DOI - 10.1111/j.1467-842x.1968.tb00216.x
Subject(s) - estimator , mathematics , statistics , normal distribution , standard deviation , distribution (mathematics) , logistic distribution , logistic regression , random variate , maximum likelihood , random variable , mathematical analysis
Summary Let g(z) be the ratio of the ordinate and the probability integral of the distribution of a variate z. The relation g(z)∼+βz is used to derive (i) estimators μ r and s̀ r of the parameters of a truncated normal distribution and (ii) estimators μ c and s̀ c of the mean and standard deviation of a logistic distribution from doubly censored samples. The variances and eovariances of these estimators are obtained. They are shown to be nearly as efficient as the maximum likelihood estimators and easier to compute.