MODEL SELECTION CRITERIA FOR LOGLINEAR MODELS

Considerable work has been devoted to developing model selection criteria for normal theory regression models. Less attention has been paid to discrete data. We develop two loglinear model selection criteria for Poisson counts. These criteria are based on an estimated bias adjustment of the Akaike information criterion. We observe in a simulation study that the corrected statistics provide good model choices and relatively accurate estimates of the mean structure.     

Tail Behavior of the Failure Rate Functions of Mixtures

The tail behavior of the failure rate of mixtures of lifetime distributions is studied. A typical result is that if the failure rate of the strongest component of the mixture decreases to a limit, then the failure rate of the mixture decreases to the same limit. For a class of distributions containing the gamma distributions this result can be improved in the sense that the behavior of the failure rate of the mixture asymptotically mirrors that of the strongest component in whether it decreases or increases to a limit. This revised version was published online in July 2006 with corrections to the Cover Date.     

Developing a Social Protection Index for Asia

Social protection is increasingly seen as an important tool for poverty reduction, but to date there have been few quantitative cross‐country assessments of social protection provision. This article develops a social protection index that systematically and consistently quantifies activities at the national level. Four summary indicators representing the cost, coverage, poverty targeting and impact are scaled and weighted to produce an additive index of the overall level of social protection provision. The index is calculated for six very different Asian countries: Bangladesh, Indonesia, Mongolia, Nepal, Pakistan and Vietnam. Considerable contrasts are revealed between their levels of social protection provision.     

Standard errors for the parameters of graphical Gaussian models

The comparison of an estimated parameter to its standard error, the Wald test, is a well known procedure of classical statistics. Here we discuss its application to graphical Gaussian model selection. First we derive the Fisher information matrix and its inverse about the parameters of any graphical Gaussian model. Both the covariance matrix and its inverse are considered and a comparative analysis of the asymptotic behaviour of their maximum likelihood estimators (m.l.e.s) is carried out. Then we give an example of model selection based on the standard errors. The method is shown to produce almost identical inference to likelihood ratio methods in the example considered.     

An economic model of teenage pregnancy decision-making

In this paper, we model unmarried teenagers' decisions about their pregnancy outcome by considering that the teenager contrasts her expected utility (1) as a married mother, (2) as an unmarried mother, or (3) after abortion. We use cross-sectional data on 297 California teenagers aged 13-19 who were pregnant for the first time between 1972 and 1974. Both Anglo and Mexican-American girls are included. We find that pregnant girls who are eligible for or are receiving public assistance are more likely to give birth and remain unmarried. Teenagers with greater time values are more likely to choose abortion, and Mexican-American girls are more likely to carry their pregnancies to term.     

A CAUTIONARY NOTE ON ENVIRONMENTAL ECONOMICS

Environmental questions have become a permanent feature of the political landscape in contemporary Australia and now play a significant role in election campaigns at both state and federal levels. Indeed, one of the most significant policy debates in the 1996 Federal election focussed on the environmental policy proposed by the Liberal/National Party coalition, which sought to fund a host of environmental programs from the proceeds of a part privatisation of Telstra. The trade-offs involved in this policy have generated substantial opposition to it and served to underline the prominence of environmental questions in Australian politics. Despite the importance of ‘the environment’ in popular thought, public debate is still typically characterised by ‘feel good’ policy announcements by politicians, sensationalist media reporting and deceptive claims by some environmental interest groups. Whilst progress has undoubtedly been made, the result has often been a plethora of inchoate and frequently conflicting policies. Not surprisingly this ‘muddle through’ approach has produced numerous instances of government intervention not only failing to meet its planned objectives but also generating unintended consequences.     

Varieties of “Fundamentalism”: a Conceptual and Empirical Analysis of Two Protestant Denominations*

Many behavioral science studies of religious fundamentalism are seriously hampered by conceptual confusion. The major source of much of this confusion is the lack of a coherent sociological definition and theoretical context for the term fundamentalism. We propose a Parsonian definition of Fundamentalism, which is interpreted in the context of a theory of evolutionary social change. The methodological implications of this approach are identified and then applied in a survey research study of the lay leaders of two historically related denominations, the Disciples of Christ and the Church of Christ. Our factor analysis of 25 questionnaire items suggests there are three types of Fundamentalism. Socio-economic variables explain some of the variation in the Fundamentalism scores, but denominational affiliation explains more. Our findings suggest that future research should use denomination-specific indices of Fundamentalism.