摘要:

The paper reviews and extends a Bayesian full information analysis of the simultaneous equations model, based upon an extended natural conjugate prior density. The extended prior density belongs to a closed family and is compatible with the independent specification for each equation of a marginal prior density in the multivariate Student form. The paper establishes properties of the resulting posterior density, of some conditional and marginal densities, and of the posterior densities in the special case of seemingly unrelated regression equations.

ISSN:0162-1459    

DOI:10.1080/01621459.1976.10480969

出版商:Taylor & Francis Group    

年代:1976

数据来源: Taylor

摘要:

An abstract general model of multiway randomized response procedures is investigated, with the aim of minimizing the variance matrix while bounding the risk to which respondents are subjected. A general result on the structure of possible optimal designs is obtained, an improved result is derived for the three-way case, and a complete answer is found for the dichotomous case.

ISSN:0162-1459    

DOI:10.1080/01621459.1976.10480970

出版商:Taylor & Francis Group    

年代:1976

数据来源: Taylor

摘要:

It Is well known that nonindependent errors arising from autoregressive (AR) or moving average (MA) processes may reverse the conclusions oftorFtests for estimable functions of regression coefficients. We show that these conclusions can be reversed only if observedtorFvalues based on ordinary least squares (OLS) computations lie between certain lower and upper bounds. Our tabulations of these bounds are based on the Imhof [5] distribution of a ratio of quadratic forms in normal variables, and avoid some of the approximations used by Watson and Hannan [16].

ISSN:0162-1459    

DOI:10.1080/01621459.1976.10480971

出版商:Taylor & Francis Group    

年代:1976

数据来源: Taylor

摘要:

A distribution-free rank procedure is proposed for use in partial discrimination problems involving two populations. It is shown that this procedure can be applied with virtually any discriminant function. Moreover, the discriminant function may be selected after observing the samples on which it is to be based. Using Monte Carlo methods the rank procedure is compared with a normal theory and a tolerance region procedure. The rank procedure was the only one that adequately controlled the probabilities of misclassification while maintaining relatively small probabilities of not classifying an observation.

ISSN:0162-1459    

DOI:10.1080/01621459.1976.10480972

出版商:Taylor & Francis Group    

年代:1976

数据来源: Taylor

摘要:

This paper investigates the distribution-free outer confidence interval for the quantile interval introduced by Wilks. Besides exact expressions and a recurrence formula some bounds are derived for the probability of correct coverage of the quantile interval which improve bounds known up to now, and which are tested in several examples. Asymptotic approximations are discussed and applications of the developed methods to other statistics based on order statistics are indicated.

ISSN:0162-1459    

DOI:10.1080/01621459.1976.10480973

出版商:Taylor & Francis Group    

年代:1976

数据来源: Taylor

摘要:

For the two-way classification model with one observation per cell the power of Tukey's single degree of freedom test for nonadditivity is compared to the power of the test for nonadditivity recently proposed by Johnson and Graybill [7].

ISSN:0162-1459    

DOI:10.1080/01621459.1976.10480974

出版商:Taylor & Francis Group    

年代:1976

数据来源: Taylor

摘要:

Consider a sequence of confidence intervals {In}. Sequential procedures are based on stopping rules which, for specified constantswandp, terminate sampling at a valuenfor whichInhas width approximatelywand noncoverage probability approximatelyp. Asymptotic analyses of such procedures have previously concerned onlyw→0withpfixed. This article presents a novel and general approach for the casep→ 0 withwfixed. Application is made to procedures based on the sample mean and median, and the corresponding asymptotic relative efficiencies are evaluated for selected values ofwfor the normal, Laplace, logistic, and uniform distributions.

ISSN:0162-1459    

DOI:10.1080/01621459.1976.10480975

出版商:Taylor & Francis Group    

年代:1976

数据来源: Taylor

摘要:

In a certain sense sample heterogeneity can only decrease the variance of a linear function of order statistics compared with that for a homogeneous sample, and thus the variance of those statistics will tend to be overestimated. The magnitude of this effect for robust estimators of location and scale is described, with particular reference to contamination models. It is shown that with asymmetric contamination, extreme observations may have much less influence on these estimators than is generally believed, if trimming is employed.

ISSN:0162-1459    

DOI:10.1080/01621459.1976.10480976

出版商:Taylor & Francis Group    

年代:1976

数据来源: Taylor

摘要:

An estimator of the parameters of a nonlinear time series regression is obtained by using an autoregressive assumption to approximate the variance-covariance matrix of the disturbances. Considerations are set forth which suggest that this estimator will have better small sample efficiency than circular estimators. Such is the case for examples considered in a Monte Carlo study.

ISSN:0162-1459    

DOI:10.1080/01621459.1976.10480977

出版商:Taylor & Francis Group    

年代:1976

数据来源: Taylor

摘要:

LetX1, …,XmandY1, …,Ynbe two independent random samples from normal populationsN(μ1, σ12) andN(μ2, σ22), respectively. The statistical problem is to testH0: μ1= μ2and σ12= σ22againstHa: μ1≠ μ2or σ12≠ σ22. Using Fisher's method of combining two independent test statistics, we suggest a test and prove that it is asymptotically optimal in the sense of Bahadur efficiency.

ISSN:0162-1459    

DOI:10.1080/01621459.1976.10480978

出版商:Taylor & Francis Group    

年代:1976

数据来源: Taylor