摘要:

DefineXas the sum of a Poisson random variableYwith parameter θ and a nonnegative integer valued variableZindependent ofY.If the distribution ofZis known,Xhas a one-parameter convoluted Poisson distribution. Such distributions are here characterized as solutions to a system of differential equations specifying the rate of change of the cumulative distribution function relative to a parametric change. The characterization is used in point and interval estimation of θ. It is shown that for a certain subclass of convoluted Poisson distributions, the maximum likelihood estimate of θ is the unique solution of the likelihood equation and is easily approximated numerically.

ISSN:0162-1459    

DOI:10.1080/01621459.1976.10480372

出版商:Taylor & Francis Group    

年代:1976

数据来源: Taylor

摘要:

LetX1, …,Xndenote a random sample from an unknown member of the family of two-parameter gamma densities

ISSN:0162-1459    

DOI:10.1080/01621459.1976.10480373

出版商:Taylor & Francis Group    

年代:1976

数据来源: Taylor

摘要:

Considernnormal populations. Random samples of equal sizemare taken from each population. It is desired to use the Bartlett procedure to test at level α the hypothesis of equal variances. A method is presented to provide exact critical values of the Bartlett test statistic. Computed exact critical values are tabulated for various (n, d, α), whered = m -1 denotes the common number of degrees of freedom.

ISSN:0162-1459    

DOI:10.1080/01621459.1976.10480374

出版商:Taylor & Francis Group    

年代:1976

数据来源: Taylor

摘要:

A Neyman-Pearson approach is taken to the problem of detecting structural shifts in naturally ordered regression problems. When the variance is known, backwards CUSUM methods are shown to maximize average power, and their application is discussed. Two methods with optimality properties for outlier detection are developed, assuming that the observations may be divided into two parts, where the first part satisfies the model assumptions, while outliers may be present in the other.

ISSN:0162-1459    

DOI:10.1080/01621459.1976.10480375

出版商:Taylor & Francis Group    

年代:1976

数据来源: Taylor

摘要:

Neyman and Scott [3] have considered the ideas of outlier-proneness and outlier-resistance of families of distributions. Under their definition, individual distributions (one-member families) cannot be outlier-prone. This paper offers definitions of outlier-proneness and outlier-resistance that apply to individual distributions, and theorems are given showing the connection with the classical laws of large numbers for maxima.

ISSN:0162-1459    

DOI:10.1080/01621459.1976.10480376

出版商:Taylor & Francis Group    

年代:1976

数据来源: Taylor

摘要:

The reciprocal moments of a linear combination of exponential variates are derived. The resultant formula is used to obtain the moments of quantile and other similar estimators for the shape parameter of a Pareto distribution. The calculations show that such estimators are more biased and less “precise” than indicated by Monte Carlo estimates of the moments previously published. The general formula for the reciprocal moments is shown to be potentially useful in linear models and in studying models of the variation in the rate of births in a pure birth process.

ISSN:0162-1459    

DOI:10.1080/01621459.1976.10480377

出版商:Taylor & Francis Group    

年代:1976

数据来源: Taylor

摘要:

Simple approximating functions for tail probabilities of the Pearson Type IV distribution are obtained by using theBntransformations of Gray, Atchison, and McWilliams [2] and by truncating the continued fraction expansion given by Shenton and Carpenter [6]. The behavior of these approximations is then investigated for various values of the parameters and levels of the tail probabilities.

ISSN:0162-1459    

DOI:10.1080/01621459.1976.10480378

出版商:Taylor & Francis Group    

年代:1976

数据来源: Taylor

摘要:

An alternative test of homogeneity of variances in samples from normal populations is developed. The performance of Bartlett's test and the new test proposed here is compared to theF-test in the case of two samples. The performance of Bartlett's test is not particularly good when samples are of unequal sizes, whereas the proposed test performs well for both equal and unequal sample sizes.

ISSN:0162-1459    

DOI:10.1080/01621459.1976.10480379

出版商:Taylor & Francis Group    

年代:1976

数据来源: Taylor

摘要:

The Emergence of Probability, Ian Hacking. New York: Cambridge University Press, 1975. 209 pp. $15.95. Reviewed by Glenn R. Shafer

ISSN:0162-1459    

DOI:10.1080/01621459.1976.10480380

出版商:Taylor & Francis Group    

年代:1976

数据来源: Taylor

摘要:

This article has no abstract

ISSN:0162-1459    

DOI:10.1080/01621459.1976.10480331

出版商:Taylor & Francis Group    

年代:1976

数据来源: Taylor