Empirical likelihood confidence regions for comparison distributions and roc curves

Abstract: The authors derive empirical likelihood confidence regions for the comparison distribution of two populations whose distributions are to be tested for equality using random samples. Another application they consider is to ROC curves, which are used to compare measurements of a diagnostic test from two populations. The authors investigate the smoothed empirical likelihood method for estimation in this context, and empirical likelihood based confidence intervals are obtained by means of the Wilks theorem. A bootstrap approach allows for the construction of confidence bands. The method is illustrated with data analysis and a simulation study.     

CORPORATE TAX GAMES WITH CROSS‐BORDER EXTERNALITIES FROM PUBLIC INFRASTRUCTURE

We construct a model of corporate tax competition in which governments also use public infrastructure investment to attract foreign direct investment, thus enhancing their tax bases. In doing so, we allow for cross‐border infrastructural externalities. Depending on the externality, governments are shown to strategically over‐ or underinvest in infrastructure. We also examine how tax cooperation influences investment in infrastructure and find that welfare may be lower under tax cooperation than under tax competition; this is the case when infrastructure is very effective in raising the tax base and generates a large negative cross‐border externality. (JEL F23, H40)     

Gambling Harm and Crime Careers

Incarcerated populations across the world have been found to be consistently and significantly more vulnerable to problem gambling than general populations in the same countries. In an effort to gain a more specific understanding of this vulnerability the present study applied latent class analysis and criminal career theory to gambling data collected from a sample of English and Scottish, male and female prisoners (N = 1057). Theoretical links between gambling and crime were tested through three hypotheses: (1) that prisoners in the UK would have higher rates of problem gambling behaviour than the national population; (2) that if the link between gambling and crime is coincidental, gambling behaviour would be highly prevalent in an offending population, and (3) if connections between gambling behaviour and offending are co-symptomatic a mediating factor would show a strong association. The first of these was supported, the second was not supported and the third was partially supported. Latent class analysis found six gambling behaviour clusters measured by responses to the Problem Gambling Severity Index, primarily distinguished by loss chasing behaviour. Longitudinal offending data drawn from the Police National Computer database found four criminal career types, distinguished by frequency and persistence over time. A significant association was found between higher level loss chasing and high rate offending in criminal careers suggesting that impulse control may be a mediating factor for both gambling harm and criminal careers.     

Consequences of Family Policies on Childbearing Behavior: Effects or Artifacts?

This article argues for a more careful consideration of theoretical and methodological approaches in studies of the effects of public policies, labeled here as family policies, on childbearing behavior. We employ elements of comparative welfare‐state research, of the sociology of “constructed categories,” and of “the new institutionalism” to demonstrate that investigations into policy effects need to contextualize policies and need to reduce their complexity by focusing on “critical junctures,”“space,” and “uptake.” We argue that the effects of family policies can only be assessed properly if we study their impact on individual behavior. Event‐history models applied to individual‐level data are the state‐of‐the‐art of such an approach. We use selected empirical studies from Sweden to demonstrate that the type of approach that we advocate prevents us from drawing misleading conclusions.     

Goodness of Fit via Non-parametric Likelihood Ratios

Abstract.  To test if a density f is equal to a specified f ₀, one knows by the Neyman–Pearson lemma the form of the optimal test at a specified alternative f ₁. Any non-parametric density estimation scheme allows an estimate of f . This leads to estimated likelihood ratios. Properties are studied of tests which for the density estimation ingredient use log-linear expansions. Such expansions are either coupled with subset selectors like the Akaike information criterion and the Bayesian information criterion regimes, or use order growing with sample size. Our tests are generalized to testing the adequacy of general parametric models, and to work also in higher dimensions. The tests are related to, but are different from, the 'smooth tests' that go back to Neyman [Skandinavisk Aktuarietidsskrift 20(1937) 149] and that have been studied extensively in recent literature. Our tests are large-sample equivalent to such smooth tests under local alternative conditions, but different from the smooth tests and often better under non-local conditions.     

Data Sharpening for Hazard Rate Estimation

Data sharpening is a general tool for enhancing the performance of statistical estimators, by altering the data before substituting them into conventional methods. In one of the simplest forms of data sharpening, available for curve estimation, an explicit empirical transformation is used to alter the data. The attraction of this approach is diminished, however, if the formula has to be altered for each different application. For example, one could expect the formula for use in hazard rate estimation to differ from that for straight density estimation, since a hazard rate is a ratio–type functional of a density. This paper shows that, in fact, identical data transformations can be used in each case, regardless of whether the data involve censoring. This dramatically simplifies the application of data sharpening to problems involving hazard rate estimation, and makes data sharpening attractive.     

„Politische Religionen“ (Eric Voegelin und Raymond Aron) — ein Begriff zur Differenzierung von Fundamentalismen?

The concept of ?political religion“ has been introduced in the late 1930s by Eric Voegelin and Raymond Aron in order to analyze the ?religious character“ of the new totalitarian political mass movements, i. e. Fascism, National Socialism and Communism, as ?collective religions of salvation“ from a critical perspective. Both abandoned the term later and replaced it by ?modern political gnosis“ or ?ersatz of religion“ (Voegelin) and ?secular religion“ (Aron). In this paper the concept and history of the term ?political religions“will be reconstructed, and the author examines the question, if it can be considered an appropriate tool of differentiation in the discussion of socalled fundamentalisms. This will be accomplished by using the example of ?radical Islamism“.     

Markt – Inklusion – Gerechtigkeit

After providing, at the outset, sketches of a number of current theoretical positions as well as empirical approaches regarding the question of justice, we will present the perspective of historico-genetic theory in greater detail. The explanatory strategy of the latter, as it relates to the postulate of justice, rests on three interlinked lines of argument: from an anthropological perspective, the thematic area of morals and justice will be connected back, in both form and substance, to the human constitution as it emerged over the course of the history of the species; from an epistemological perspective, the development of cognition and the capacity to engage in reflection will be connected structurally and processually to the development of forms of society, in the process reconstructing the genesis of the normative postulate of justice; finally, from a social-theoretical perspective, the question will be posed under which conditions social justice has been demanded in the course of societal development resting on processes of power—and how it can be made valid. In conclusion, we will briefly introduce individual contributions with regard to how they connect with the historico-genetic theory.     

PREDICTION-FOCUSED MODEL SELECTION FOR AUTOREGRESSIVE MODELS

In order to make predictions of future values of a time series, one needs to specify a forecasting model. A popular choice is an autoregressive time‐series model, for which the order of the model is chosen by an information criterion. We propose an extension of the focused information criterion (FIC) for model‐order selection, with emphasis on a high predictive accuracy (i.e. the mean squared forecast error is low). We obtain theoretical results and illustrate by means of a simulation study and some real data examples that the FIC is a valid alternative to the Akaike information criterion (AIC) and the Bayesian information criterion (BIC) for selection of a prediction model. We also illustrate the possibility of using the FIC for purposes other than forecasting, and explore its use in an extended model.     

Admission of Puerto Rico to the Union of States: Unityis the issue

Proposed Congressional legislation would allow the status of Puerto Rico—as an associated Commonwealth, an independent country, or a state of the United States—to be decided by popular plebiscite in Puerto Rico. The proposed legislation is silent on language policy, an issue of concern to many Americans and which has been much discussed in Puerto Rico. In addition to the divisiveness inherent in bilingualism, the history of the island's relations with the United States raises concern that statehood might lead to a separatist backlash possibly accompanied by violent unrest. The authors urge wider debate and a more deliberate approach to union: one that does not attempt to displace the Spanish tradition but one which protects the traditional language unity of the United States.The authors are public policy analysts who have worked extensively on issues relating to the status of English in the United States. The views expressed in this article are their own, and do not necessarily reflect those of any group or constituency.