摘要:

AbstractThe results of a Monte Carlo study of the sensitivity of Rosenblatt density estimates to the scale factor are presented.

ISSN:0319-5724    

DOI:10.2307/3314975

出版商:Wiley‐Blackwell    

年代:1983

数据来源: WILEY

摘要:

AbstractIn this paper we prove a theorem on “asymptotically independent” Gaussian sequences. This result improves and simplifies a result of Lai (1973) on lower classes of Gaussian sequen

ISSN:0319-5724    

DOI:10.2307/3314976

出版商:Wiley‐Blackwell    

年代:1983

数据来源: WILEY

摘要:

AbstractThe asymptotic properties of the maximum‐likelihood estimator of the parameter vector for a class of birth‐and‐death processes admitting a unique stationary distribution are studied. Also, it is shown that identifiability of the parameter vector with respect to the likelihood implies that the Fisher information matrix is of full rank. Two special cases of biological interest are presented. One of these, the exponential birth‐and‐death process, is proposed as a more appropriate model of density dependence than the logisti

ISSN:0319-5724    

DOI:10.2307/3314977.n

出版商:Wiley‐Blackwell    

年代:1983

数据来源: WILEY

摘要:

AbstractNecessary and sufficient conditions for equalities between the best linear unbiased estimator, the weighted least‐squares estimator, and the simple least‐squares estimator of the expectation vector in a general Gauss‐Markoff model are given in some alternative formulations. The main result states, somewhat surprisingly, that the weighted least‐squares estimator cannot be identical with the simple least‐squares estimator unless they both coincide with the best linear unbiased

ISSN:0319-5724    

DOI:10.2307/3314978

出版商:Wiley‐Blackwell    

年代:1983

数据来源: WILEY

摘要:

Nous étudions le problème de tester, dans une population normalep‐dimensionnelle de moyenne μ et de matrice de covariance ∑ inconnue, l'hypothèse nulle ℋ︁0: μ1= 0, μ ≥ 0 versus l'alternative ℋ︁1: μ ≠ 0 ou μ2≱ 0, où μ′ =(μ′1, μ′2). Nous dérivons le test à rapport de vraisemblance maximale, nous montrons que le test découlant du principe d'union‐inter‐section est le même, nous démontrons l'admissibilité de ce tes

ISSN:0319-5724    

DOI:10.2307/3314979

出版商:Wiley‐Blackwell    

年代:1983

数据来源: WILEY

摘要:

AbstractThis article presents some structural properties of the inverse Gaussian distribution, together with several new characterizations based on constancy of regression of suitable functions on the sum ofnindependent identically distributed random variables. A decomposition of the statistic λσ in=1(X−1i−X−1) inton‐ 1 independent chi‐squared random variables, each with one degree of freedom, is given whennis o

ISSN:0319-5724    

DOI:10.2307/3314980

出版商:Wiley‐Blackwell    

年代:1983

数据来源: WILEY

摘要:

AbstractThe two‐parameter lognormal distribution with density functionf(y: γ, σ2) = [(2πσ2)1/2y]1exp[−(lny− γ)2/2σ2],y>0, is important as a failure‐time model in life testing. In this paper, Bayesian lower bounds for the reliability functionR(t: γ, σ2) = ϕ[(γ − lnt)/σ] are obtained for two cases. First, it is assumed that γ is known and σ2has either an inverted gamma or “general uniform” prior distribution. Then, for the case that both γ and σ2are unknown, the normal‐gamma prior and Jeffreys' vague prior are considered. Some Monte Carlo simulations are given to indicate some of the propertie

ISSN:0319-5724    

DOI:10.2307/3314981

出版商:Wiley‐Blackwell    

年代:1983

数据来源: WILEY

摘要:

AbstractA simple three‐moment approximation is introduced for the distribution of the sample variance. Comparisons are given with other approximations discussed by Tan and Wong (1977) and with an approximation developed very recently by Mudholkar and Trivedi (1981

ISSN:0319-5724    

DOI:10.2307/3314977

出版商:Wiley‐Blackwell    

年代:1983

数据来源: WILEY

摘要:

AbstractWe consider maximum‐likelihood estimators of the three parameters in the Weibull distribution. Motivated by an application regarding the determination of a lower percentile of the strength of dimension lumber, we investigate the sampling properties of these estimators. Consistency is established when the shape parameter is greater than one, including some nonregular cases encountered in fitting lumber data. The joint distribution of the estimators is studied by a Monte Carlo approach. The maximum‐likelihood estimator of the 5th percentile is compared with the sample 5th percentile. For the cases considered it was generally found that with sample size 70 the usual asymptotic normality does not h

ISSN:0319-5724    

DOI:10.2307/3314983

出版商:Wiley‐Blackwell    

年代:1983

数据来源: WILEY

ISSN:0319-5724    

DOI:10.2307/3314984

出版商:Wiley‐Blackwell    

年代:1983

数据来源: WILEY