摘要:

A wide variety of paired-comparison experiments and surveys may be viewed within the framework of “incomplete” contingency table analysis. Bradley-Terry models for such data can be chosen and further examined by a noniterative logit analysis. Multivariate paired comparisons with factor structure can be analyzed through reparameterization of the underlying models for each combination of factor levels. The method is subject to sample-size restrictions but allows the experimenter to design his survey without complex symmetry conditions or independence assumptions.

ISSN:0162-1459    

DOI:10.1080/01621459.1976.10481537

出版商:Taylor & Francis Group    

年代:1976

数据来源: Taylor

摘要:

A family of rank statistics based on a set of simple scores functions is introduced. The distribution theory is briefly discussed, and both point and interval estimators for the center of an absolutely continuous symmetric distribution are presented. Given a random sample from a symmetric distribution, all subsequent inference is based on the member of the family of rank statistics having the smallest estimated asymptotic variance. The robustness properties are examined using the results of a simulation study.

ISSN:0162-1459    

DOI:10.1080/01621459.1976.10481538

出版商:Taylor & Francis Group    

年代:1976

数据来源: Taylor

摘要:

This paper considers a system of two seemingly unrelated equations. Without imposing any additional restrictions on the matrices of observations on the independent variables in the two equations, we derive the exact second moments of Zellner's estimator [9]. Though not uniformly more efficient than the corresponding single-equation least-squares estimator, a definite efficiency gain results using Zellner's estimator in the presence of high contemporaneous correlation coefficient (ρ) between the disturbances in the two equations, and little loss results when the true ρ is small and the excess of the sample size over the number of distinct regressors in this system is greater than 12.

ISSN:0162-1459    

DOI:10.1080/01621459.1976.10481539

出版商:Taylor & Francis Group    

年代:1976

数据来源: Taylor

摘要:

This paper develops some efficient algorithms for linear spline and piecewise multiple linear regression. A plotting procedure that shows the existence and location of changes in linear regression models is developed as an adjunct to one of the algorithms. The algorithms are compared with other presently available algorithms both in terms of efficiency and in terms of performance on sets of artificial data. An example shows how the algorithms, implemented in portable FORTRAN IV, can be used profitably in the analysis of data.

ISSN:0162-1459    

DOI:10.1080/01621459.1976.10481540

出版商:Taylor & Francis Group    

年代:1976

数据来源: Taylor

摘要:

Randomized response methods allow different kinds and degrees of privacy depending upon models and parameters. A theoretical approach to efficiency is suggested based on minimizing variance for given privacy requirements. Privacy requirements are defined in units of jeopardy from different points of view and indexed by measures suggested by information theory. Variances of competing models are compared only when the procedures meet the privacy requirements in terms of not exceeding the maximal jeopardizing information allowable for the particular application. The approach is illustrated through developing minimum variance under given jeopardizing information restrictions for a general dichotomous-population-dichotomous-response model.

ISSN:0162-1459    

DOI:10.1080/01621459.1976.10481541

出版商:Taylor & Francis Group    

年代:1976

数据来源: Taylor

摘要:

The linear least-squares prediction approach is applied to some problems in two-stage sampling from finite populations. A theorem giving the optimal (BLU) estimator and its error-variance under a general linear “superpopulation” model for a finite population is stated. This theorem is then applied to a model describing many populations whose elements are grouped naturally in clusters. Next, the probability model is used to analyze various conventional estimators and certain estimators suggested by the theory as alternatives to the conventional ones. Problems of design are considered, as are some consequences of regression-model failure.

ISSN:0162-1459    

DOI:10.1080/01621459.1976.10481542

出版商:Taylor & Francis Group    

年代:1976

数据来源: Taylor

摘要:

When the entries in a contingency table arise from clustered sampling, the chi-squared statistic conventionally calculated to testsimple and complex hypotheses about the parameters of the table may not have the distribution of a χ2variate. Assuming a model for positively associated clustering, this article finds the distribution of the conventional chi-squared statistic and shows how to correct it to an asymptotically χ2variate. A numerical example from the epidemiology of mental illness is given.

ISSN:0162-1459    

DOI:10.1080/01621459.1976.10481543

出版商:Taylor & Francis Group    

年代:1976

数据来源: Taylor

摘要:

A very general procedure for the sequential construction of D-optimal designs is given, which includes Wynn's procedure as a special case. An example is presented to compare various alternative procedures. Properties of the weightsαnin these procedures are discussed, and the convergence rate of Fedorov's procedure is obtained.

ISSN:0162-1459    

DOI:10.1080/01621459.1976.10481544

出版商:Taylor & Francis Group    

年代:1976

数据来源: Taylor

摘要:

This article gives three new tests of hypotheses concerning the parameters of von Mises distributions, derived from the likelihood ratio statistics. The two principal tests are for equality of small dispersion parameters where the modal vectors are known and for equality of modal vectors given an unknown common dispersion parameter, assumed large. The tests are simple to use, and are easily adapted for axial data.

ISSN:0162-1459    

DOI:10.1080/01621459.1976.10481545

出版商:Taylor & Francis Group    

年代:1976

数据来源: Taylor

摘要:

A new estimator utilizing multiauxiliary information in survey sampling is constructed. This estimator is unbiased for the population mean and has a smaller variance than Des Raj's optimal estimator [1, 2]. The new estimator and the latter one are based on the same amount of information.

ISSN:0162-1459    

DOI:10.1080/01621459.1976.10481546

出版商:Taylor & Francis Group    

年代:1976

数据来源: Taylor