ISSN:0162-1459    

DOI:10.1080/01621459.1980.10477413

出版商:Taylor & Francis Group    

年代:1980

数据来源: Taylor

摘要:

Several graphical statistical methods tailored particularly for clustering applications are described and discussed. Certain techniques give ways of examining the internal cohesiveness of clusters, both across all variables and in terms of particular variables. Other graphical methods are concerned with relationships within and between clusters and with variables exogenous to the clustering. The methods focus on changes in cluster characteristics across two successive time periods. These techniques are illustrated with data from a cluster analysis using economic characteristics of 48 firms from one industry.

ISSN:0162-1459    

DOI:10.1080/01621459.1980.10477414

出版商:Taylor & Francis Group    

年代:1980

数据来源: Taylor

摘要:

This study provides conditions under which several well-known and easily computable statistics for testing nonnormality (√b1,b2,D, W′, W) can be modified for large-sample use in the classical linear regression framework by replacing the true stochastic error with the least squares residual. Monte Carlo simulations indicate that the modified statistics perform acceptably well even forn= 35. None of the tests clearly dominates the others, although the modified version ofW′performs well for moderate sample sizes, while the modifiedDand omnibusRtest, based on joint use of √b1andb2, perform well for larger samples (n= 50, 100). We illustrate the use of normality tests using a recent empirical study by Lillard and Willis.

ISSN:0162-1459    

DOI:10.1080/01621459.1980.10477415

出版商:Taylor & Francis Group    

年代:1980

数据来源: Taylor

ISSN:0162-1459    

DOI:10.1080/01621459.1980.10477416

出版商:Taylor & Francis Group    

年代:1980

数据来源: Taylor

摘要:

Within the errors-in-variables framework, a model of consumer behavior that includes permanent and transitory income is estimated from the 1952 Oxford Savings Survey data and used to test the assumptions of the permanent-income hypothesis. The analysis is extended to the case in which the variables determining permanent income and the case in which the variables determining transitory income are measured with error. In the former case, the tests of the permanent-income model remain valid, but in the latter case errors in measurement lead to a reduction in the estimate of the marginal propensity to consume out of transitory income.

ISSN:0162-1459    

DOI:10.1080/01621459.1980.10477417

出版商:Taylor & Francis Group    

年代:1980

数据来源: Taylor

摘要:

Saboia (1977) has developed a theory relating a particular type of births autoregressive moving average (ARMA) model to the classical deterministic cohort model of population growth. Reexamination of the data used by Saboia indicates that his estimated births models contain common factors and insignificant coefficients and cannot be regarded as evidence in favor of his argument. It is shown, however, that well-known theory on the relationship between deterministic and stochastic structural models and ARMA processes does provide the link and that Saboia's argument can be regarded as a special case of this general theory.

ISSN:0162-1459    

DOI:10.1080/01621459.1980.10477418

出版商:Taylor & Francis Group    

年代:1980

数据来源: Taylor

摘要:

The (maximum) penalized-likelihood method of probability density estimation and bump-hunting is improved and exemplified by applications to scattering and chondrite data. We show how the hyperparameter in the method can be satisfactorily estimated by using statistics of goodness of fit. A Fourier expansion is found to be usually more expeditious than a Hermite expansion but a compromise is useful. The best fit to the scattering data has 13 bumps, all of which are evaluated by the Bayesian interpretation of the method. Eight bumps are well supported. The result for the chondrite data suggests that it is trimodal and confirms that there are (at least) three kinds of chondrite.

ISSN:0162-1459    

DOI:10.1080/01621459.1980.10477419

出版商:Taylor & Francis Group    

年代:1980

数据来源: Taylor

ISSN:0162-1459    

DOI:10.1080/01621459.1980.10477420

出版商:Taylor & Francis Group    

年代:1980

数据来源: Taylor

ISSN:0162-1459    

DOI:10.1080/01621459.1980.10477421

出版商:Taylor & Francis Group    

年代:1980

数据来源: Taylor

ISSN:0162-1459    

DOI:10.1080/01621459.1980.10477422

出版商:Taylor & Francis Group    

年代:1980

数据来源: Taylor