摘要:

Livingston survey data from 1958 to 1971 are used to test the hypothesis that price expectations are normally distributed across the respondents to each survey. If the forecasts of the CPI and WPI are grouped around integers, chi-square tests indicate that normality is not a bad hypothesis. On balance, however, the sample distributions are skewed to the right and more peaked than the normal. Other distributions were therefore tried and even better fits obtained with a scaled logt-distribution.

ISSN:0162-1459    

DOI:10.1080/01621459.1975.10480299

出版商:Taylor & Francis Group    

年代:1975

数据来源: Taylor

摘要:

To analyze the “scalability” of the observed response patterns for a set ofmdichotomous items, we introduce a model in which a given individual in the population is either “intrinsically scalable” or “intrinsically unscalable” (with respect to themitems), and there areddifferent types of “intrinsically scalable” individuals. With this model, using methods already developed for the study of quasi-independence in contingency tables, we show how to (a) test whether the model fits the observed data, (b) estimate the proportion of intrinsically scalable (and unscalable) individuals, and (c) estimate the distribution of the intrinsically scalable individuals among theddifferent scale types.

ISSN:0162-1459    

DOI:10.1080/01621459.1975.10480300

出版商:Taylor & Francis Group    

年代:1975

数据来源: Taylor

摘要:

In the presence of multicollinearity ridge regression techniques result in estimated coefficients that are biased but have a smaller variance than ordinary least squares (OLS) estimators and may, therefore, have a smaller mean square error. The directed ridge estimator (DRE) suggested here alters only diagonal elements corresponding to relatively small eigenvalues. The advantage of our method is that the resulting estimates may be less biased than in other ridge regression methods that alter all diagonal elements. A set of experiments indicate that various ridge estimators result in reduced mean square error in the coefficient estimates relative to OLS and that DRE performs well relative to the others.

ISSN:0162-1459    

DOI:10.1080/01621459.1975.10480301

出版商:Taylor & Francis Group    

年代:1975

数据来源: Taylor

摘要:

A sample-based procedure for selecting an optimal subset of variables for the two-group multinomial classification problem is presented. Based on the work of Glick, we examine two variations of a procedure which looks at differences in discriminant scores as a method for assessing worthiness of various subsets of variables. Two examples illustrate the methods.

ISSN:0162-1459    

DOI:10.1080/01621459.1975.10480302

出版商:Taylor & Francis Group    

年代:1975

数据来源: Taylor

摘要:

The likelihood ratio classification rule is derived from the location model, applicable when the data contains both binary and continuous variables. A method is proposed for estimating the rule in practical situations and assessing its performance. Losses incurred by the estimation procedure are investigated, and use of Fisher's linear discriminant function on such data is studied for the case of known population parameters. Finally, the proposed rule is applied to some data sets, and its performance is compared with that of some other classification rules.

ISSN:0162-1459    

DOI:10.1080/01621459.1975.10480303

出版商:Taylor & Francis Group    

年代:1975

数据来源: Taylor

摘要:

Several nonparametric and parametric statistics for testing the equality of scale parameters are compared with respect to their power and stability of error rates. When the populations have mass confined to the positive axis, thec-sample analog of the sum of squared ranks test and the Kruskal-Wallis test are found to be very robust and powerful. When the populations are symmetrical, thec-sample analogs of the two-sample Mood and two-sample Ansari-Bradley tests are robust for small samples, and are more powerful than Box's test. Tables of exac probabilities and corresponding critical values of the nonparametric statistics are given for testing the equality of scales for small samples.

ISSN:0162-1459    

DOI:10.1080/01621459.1975.10480304

出版商:Taylor & Francis Group    

年代:1975

数据来源: Taylor

摘要:

The objectives of this study are twofold. First, a simultaneous-equations model that takes into account the interactions between various economic aspects of urban growth and migration to and from urban areas is specified. Second, the model is estimated for two different time periods, 1950–60 and 1960–70, with the Standard Metropolitan Statistical Area as the basic urban geographic unit. Included among the jointly dependent variables are civilian labor force out-migration, civilian labor force in-migration, income change, manufacturing employment change, government employment change, other nonmanufacturing employment change, and unemployment change. Significant interactions among the various endogenous variables are uncovered for both time periods studied.

ISSN:0162-1459    

DOI:10.1080/01621459.1975.10480305

出版商:Taylor & Francis Group    

年代:1975

数据来源: Taylor

摘要:

Tate and Hyer [9] indicated in a recent article that the χ2test of goodness of fit is markedly in error when expected frequencies are small, and that, moreover, errors of substance remain even with large expected frequencies. This result appears to arise from the application of an improper statistical model. When the multinomial test proposed here is substituted, it is found that errors of the χ2test are smaller than Tate and Hyer would suggest for small expected frequencies, and negligible for large expected frequencies. These empirical results support the logical arguments presented here in favor of the proposed “Exact χ2Test.”

ISSN:0162-1459    

DOI:10.1080/01621459.1975.10480306

出版商:Taylor & Francis Group    

年代:1975

数据来源: Taylor

摘要:

Eight hundred fifty-four high school students' responses were employed to compare drug-use estimates derived from either (a) traditional direct questioning regarding use of six drugs, or (b) a more indirect and more anonymous method of inquiry, the randomized response procedure. Results indicated that (1) the randomized response procedure produced significantly fewer response refusals, and (2) significantly higher drug-use estimates supported the hypothesized greater sensitivity and validity of the randomized response procedure. The results further suggested that previous estimates derived from standard forms of questioning many haveunderestimatedincidence of drug-use.

ISSN:0162-1459    

DOI:10.1080/01621459.1975.10480307

出版商:Taylor & Francis Group    

年代:1975

数据来源: Taylor

摘要:

Recently the Bureau of the Census used repeated orthogonal replications to estimate the variance for one of its surveys. This article explains how the proper replication patterns were selected, and gives a step-by-step general method for obtaining orthogonal replications.

ISSN:0162-1459    

DOI:10.1080/01621459.1975.10480308

出版商:Taylor & Francis Group    

年代:1975

数据来源: Taylor