摘要:

The evaluation of social programs is typically hampered by serious methodological problems. Adopting the approach of Bayesian simultaneous estimation proposed by Lindley and Smith (1972) and operationally developed by Jackson, Novick, and Thayer (1971), Novick, Lewis, and Jackson (1973), and Lewis, Wang, and Novick (1975), we demonstrate how some of these problems can be avoided or solved. To accomplish this, we extend the operational method to marginalm-group mean analysis for the unbalanced case. Data from the Emergency School Aid Act (ESAA) evaluation are used for illustration. Bayesianm-group analysis techniques are applied to data gathered from 17 school districts to evaluate the effectiveness of each district's compensatory education program.

ISSN:0162-1459    

DOI:10.1080/01621459.1977.10479947

出版商:Taylor & Francis Group    

年代:1977

数据来源: Taylor

摘要:

We assess biases due to measurement errors in structural equation models of the intergenerational transmission of socioeconomic status. Using data for nonblack males from the 1973 Occupational Changes in a Generation-II survey, we find that retrospective reports of status variables are as reliable as contemporaneous reports and that response errors are strictly random. When measurement errors are ignored, occupational returns to schooling are underestimated by about ten percent, the effects of some background variables are underestimated by as much as 19 percent, and residual variation in socioeconomic achievements is underestimated by as much as 16 percent.

ISSN:0162-1459    

DOI:10.1080/01621459.1977.10479948

出版商:Taylor & Francis Group    

年代:1977

数据来源: Taylor

摘要:

Various methods of estimating and testing the relative effectiveness of advertising campaigns using split-cable TV consumer panel data are examined. Sensitivities of the methods to missing observations, serial correlation, and the pattern of the expected advertising campaign impact over time are considered. The maximum likelihood estimators for both the case of no missing observations and the missing-observations case are derived, and a nonlinear model which allows for a gradual diffusion of the relative impact of the campaign is developed. For the data analyzed, the nonlinear model is best for discerning a significant difference between campaigns.

ISSN:0162-1459    

DOI:10.1080/01621459.1977.10479949

出版商:Taylor & Francis Group    

年代:1977

数据来源: Taylor

摘要:

Given a series of consecutive measurements on a random sample of individuals, it is often of interest to investigate whether there exists a relationship between the rate of change and the initial value. Assuming that the observations deviate in a random manner from the true values, straightforward regression computations will yield biased results. It is shown that, in the case of the normal distribution, the maximum likelihood (ML) estimates of the second-order moments of the true slope and the true initial value are obtained by simple adjustments of the corresponding moments of the estimated quantities. An asymptotic formula for the standard error of the regression coefficient of slope on initial value is derived, and the methods are applied to longitudinal blood pressure data. The case with concomitant variables is discussed briefly.

ISSN:0162-1459    

DOI:10.1080/01621459.1977.10479950

出版商:Taylor & Francis Group    

年代:1977

数据来源: Taylor

摘要:

In this article we introduce the problem of computer software reliability and discuss a probabilistic model for describing the failure of software. We suggest a procedure for estimating the parameters of the model and propose a stopping rule for debugging the software. We apply our procedures to some published data on software failures.

ISSN:0162-1459    

DOI:10.1080/01621459.1977.10479951

出版商:Taylor & Francis Group    

年代:1977

数据来源: Taylor

摘要:

This work considers estimation of dichotomous characteristics of rare populations by sample survey. In particular, we investigate optimum allocation when anetwork samplingrule (also calledmultiplicityrule) is used to link members of the rare population to enumeration units and when the enumeration units are chosen by stratified random sampling. For this situation, formulas are derived for optimum allocation under the restriction that an enumeration unit is linked to at most one member of the rare population, and the cost efficiency of network sampling rules is compared to that of conventional enumeration rules.

ISSN:0162-1459    

DOI:10.1080/01621459.1977.10479952

出版商:Taylor & Francis Group    

年代:1977

数据来源: Taylor

摘要:

This article presents estimates of the elasticities of substitution among capital and up to 12 sex-occupation categories of labor, as well as each input's elasticity of demand, for 12 U.S. manufacturing industries in 1960. These values are derived from a cross-section production function model using states as observations, estimated with data from the Censuses of Manufacturing and Population. The estimator is a nonlinear iterative Zellner procedure, which produces full-information maximum likelihood estimates in this particular application. The results indicate that aggregation of labor into one or two categories is inconsistent with the data in most industries and that capital-skill complementarity is not universal in U.S. manufacturing.

ISSN:0162-1459    

DOI:10.1080/01621459.1977.10479953

出版商:Taylor & Francis Group    

年代:1977

数据来源: Taylor

摘要:

A method is developed for assigning a probability to a fingerprint, including a partial print, based on the number of individual (Galton) characteristics present. A multinomial model is used, the categories of which are the individual characteristics and combinations of them. The negative of the logarithm of the probability of any particular configuration is related to the entropy function of information theory. The parameters of the model are estimated from data (fingerprints). Confidence bounds are obtained for the negative log probability of any configuration.

ISSN:0162-1459    

DOI:10.1080/01621459.1977.10479954

出版商:Taylor & Francis Group    

年代:1977

数据来源: Taylor

摘要:

This article contains a bibliography of papers on multiple comparisons between 1966 and 1976. A discussion of some of the more important developments during this period precedes the bibliography.

ISSN:0162-1459    

DOI:10.1080/01621459.1977.10479955

出版商:Taylor & Francis Group    

年代:1977

数据来源: Taylor

摘要:

Procedures are given for assessing the conclusiveness of a decision in terms of a (chance) conditional confidence coefficient Γ that has frequentist interpretability analogous to that of a traditional confidence coefficient. Properties of such procedures are compared in terms of the distribution of Γ. This leads to recommendations on the choice of conditioning. Also, a methodology for estimating the confidence when it depends on unknown parameter values is given. The notions of confidence are not limited to interval estimation; examples are also given in hypothesis testing and selection problems and in nonparametric and sequential settings.

ISSN:0162-1459    

DOI:10.1080/01621459.1977.10479956

出版商:Taylor & Francis Group    

年代:1977

数据来源: Taylor