MAXIMUM-LIKELIHOOD-ESTIMATION OF MEANS AND VARIANCES FROM NORMAL-POPULATIONS UNDER SIMULTANEOUS ORDER RESTRICTIONS

[摘要] For k normal populations with unknown means mu(i) and unknown variances sigma(i)2 i = 1, ..., k, assume that there are some order restrictions among the means and variances, respectively, for example, simple order restrictions: mu1 less-than-or equal-to mu2 less-than-or-equal-to ... less-than-or-equal-to mu(k) and sigma1(2) greater-than-or-equal-to sigma2(2) greater-than-or-equal-to ... greater-than-or-equal-to sigma(k)2>0. Some properties of maximum likelihood estimation of mu(i)s and sigma(i)2 are discussed and an algorithm of obtaining the maximum likelihood estimators under the order restrictions is proposed. (C)) 1994 Academic Press, Inc.

[发布日期] 1994-08-01

[关键词] ISOTONIC REGRESSION;RESTRICTED MAXIMUM LIKELIHOOD ESTIMATION;PARTIAL ORDER;ITERATION METHOD