Reporting missing data: a study of selected articles published from 2003–2007

Missing data (MD) is prevalent in empirical social science research (Allison, http://books.google.ca/books?id=ZtYArHXjpB8Canddq=missing+dataandprintsec=frontcoverandsource=blandots=ziTBvDHxWbandsig=Uiy83xDbWSO4HeBSth0Q_oZIrQandhl=enandei=q6A7Su25ApnIM-eYlccOandsa=Xandoi=book_resultandct=resultandresnum, 2001; Rubin in J Am Stat Assoc 91:473?C489, 1996). Furthermore, inconsistencies in the reporting and treatment of MD have been documented (Peugh and Enders in Rev Educ Res 74:525?C556, 2004). The goal of the current project was to examine how MD was reported and treated in 68 studies issued from a refereed educational journal. It was observed that a fifth of the quantitative articles reviewed actually treated MD, using mainly deletion methods and only 10% of the explicit articles explained MD. Overall, MD reported or inferred averaged about 33% of cases and was commonly associated with missing subjects. Only three articles provided the actual percentages of MD. The results suggest that there may be a lack of consistency in how MD is reported and treated and that studies may remain deficient in how MD is addressed. The importance of the study was to signal tendencies in reporting and treating MD, to provide tentative explanations for such trends, to propose hypotheses for future empirical studies in the field, and to offer an initial set of practical guidelines for including addressing, explaining, and treating MD in educational research.     

Testing for Parameter Stability in Dynamic Models across Frequencies*

This paper contributes to the econometric literature on structural breaks by proposing a test for parameter stability in vector autoregressive (VAR) models at a particular frequency ω, where ω ∈ [0, π]. When a dynamic model is affected by a structural break, the new tests allow for detecting which frequencies of the data are responsible for parameter instability. If the model is locally stable at the frequencies of interest, the whole sample size can then be exploited despite the presence of a break. The methodology is applied to analyse the productivity slowdown in the US, and the outcome is that local stability concerns only the higher frequencies of data on consumption, investment and output.     

Banking and Debt Crises in Europe: The Dangerous Liaisons?

The potential mutation of the Sub-Prime banking crisis into a sovereign debt one in Euro area countries is investigated. After reviewing the criteria used to measure the debt vulnerability, the balance sheet approach is presented in order to illustrate the potential connections between these two types of crises. A graphical analysis yields evidence that at the end 2009 the probability of observing a Euro area country defaulting is less likely than six month before. Nevertheless, the serious threats, which concern Greece and Ireland, do not permit us to exclude the occurrence of a contagious, or self-fulfilling, sovereign debt or currency crises in Euro area in the future.     

An Alternative View on Regulatory Distortions in a Competitive Financial Services Industry

We present an alternative view on regulatory distortions in the banking industry. We use the duopoly model developed by Boot, Dezelan, and Milbourn (BDM, 2000), where a bank with low monitoring costs faces a bank with high monitoring costs. We show that when the initial level of the capital requirement is low, an increase of the minimum ratio between capital and total assets causes a higher decrease in profits at the bad bank than at the good bank. This finding contrasts with BDM's theorem 1, which predicts that a regulation imposing an identical increase in production costs on both banks will cause a greater loss in profits at the good bank than at the bad bank. We also look at the impact of an increase in the minimum ratio between capital and total assets on the profits of a representative bank in three other competitive environments identified in BDM. We find that the decrease in the representative bank's profit caused by an increase in the capital requirement is larger when the bank faces competition from an unregulated firm than when it faces a regulated competitor or no competitor at all. This result is consistent with BDM's theorem 2.     

Mutual impacts of product standardization and supply chain design

This paper deals with two major issues for industries; the product design and the supply chain design. These problems are usually solved separately, but in recent years, approaches were proposed to tackle these two problems together. In this paper, we investigate more precisely the links between the standardization of products or components, and the design of the supply chain. First, we show on a little example that there is a great interest to consider simultaneously these two decisions, and that solving these interdependent problems separately could result in a suboptimal, or even a bad, decision. Then, on a simplified problem issued from an industrial case study, we outline the impact of standardization choices on the structure of the supply chain and the gain that can be obtained from solving the problem as a unique compound optimization model. To illustrate the solutions of the problem, we propose graphics in order to visualize, in function of quantities and/or transportation costs, the best decision for the product standardization and for the supply chain design. Graphics also permit to anticipate the impacts of a variation of either quantities or transportation costs, from a specific situation. Such graphics they could be used in a decision aid tool to help companies in their choices. Finally, we show that costs and supply chain structure are highly impacted.     

Survey on attitudes to nutrition planning

The results of a worldwide survey of nutrition planning professionals' attitudes towards nutrition policy are presented. The objective of the survey was to determine what those involved in nutrition planning perceive to be the causes of hunger and malnutrition, and their views on the effectiveness of the programs implemented to overcome these problems. In mid-1979, a questionnaire was compiled comprising 48 questions related to attitudes towards nutrition policy, voluntary questions about social class, political classification and professional behavior and a question on perceived major impediments to solving malnutrition in the world. The questionnaire was sent to 728 professionals 87 countries; 250 replies from 55 countries; 250 replies from 55 countries were received. 44% of respondents resided in the US, 16% in Latin America and the Caribbean, 14% in the Far East, 12% in Africa and the Middle East and 13% in Europe, Canada and Australasia. Self-classification of political beliefs is the most clear cut correlate in predicting attitudes towards food and nutrition policy. There appear to be 2 clear schools of scientific/political behavior in the sample: one holds a more moderate, but generally liberal, set of views regarding the failure of modern technology in resolving world hunger and nutrition problems; a 2nd more liberal group believes political causes to be at the root of hunger. There is no single profession that can be typified as a breeding ground for nutrition planners. While the European trained and/or native group tends to be more to the left in their attitudes than their counterparts in the US, both groups are decidedly liberal and believe that social structural changes are needed to solve the problems of hunger and malnutrition in the world.     

Storage and security of supply in the medium run

This paper analyzes the role of private storage in a market for a commodity (e.g. natural gas) whose supply is subject to the threat of an irreversible disruption. We focus on the medium term in which seasonality of demand and exhaustibility can be neglected. We characterize the price and inventory dynamics (accumulation, drainage and limit stocks) in a competitive equilibrium with rational expectations. We show the robustness of our results to alternative scenarios in which either a disruption has finite duration or the crisis is foreseen. During the crisis consumers may put pressure on the Government to intervene, but too severe antispeculative measures would inefficiently discourage storage. Practical solutions to this dilemma cause welfare losses that we characterize and quantify.     

The Consequences for a Monopolistic Insurance Firm of Evaluating Risk Better than Customers: The Adverse Selection Hypothesis Reversed

This article models a situation in which a monopolistic insurer evaluates risk better than its customers. The resulting equilibrium allocations are compared to the consequences of the standard adverse selection hypothesis. On the positive side, they exhibit the property that low-risk people are better covered than higher-risk people. On the normative side, the article shows that there are two reasons for avoiding excessive risk classification: one is the classical destruction of insurance possibilities, and the other comes from the distrustful atmosphere generated by new asymmetric information.     

An analysis of housing expenditure using semiparametric cross-section models

In this paper we model expenditure on housing for owners and renters by means of endogenous switching regression models using cross-section data. We explain the share of housing in total expenditure from family characteristics and total expenditure, where the latter is allowed to be endogenous. We apply various existing parametric and semiparametric techniques for cross-section data. Exogeneity of total expenditure is rejected for the parametric models but not for most semiparametric models. The results are compared on the basis of budget elasticities and graphs of the estimated relationship between the budget share spent on housing and the logarithm of total expenditure. First version received: November 1997 / Final version received: January 2000