Methods for Default and Robust Bayesian Model Comparison: the Fractional Bayes Factor Approach

In the Bayesian approach to model selection and hypothesis testing, the Bayes factor plays a central role. However, the Bayes factor is very sensitive to prior distributions of parameters. This is a problem especially in the presence of weak prior information on the parameters of the models. The most radical consequence of this fact is that the Bayes factor is undetermined when improper priors are used. Nonetheless, extending the non-informative approach of Bayesian analysis to model selection/testing procedures is important both from a theoretical and an applied viewpoint. The need to develop automatic and robust methods for model comparison has led to the introduction of several alternative Bayes factors. In this paper we review one of these methods: the fractional Bayes factor (O'Hagan, 1995). We discuss general properties of the method, such as consistency and coherence. Furthermore, in addition to the original, essentially asymptotic justifications of the fractional Bayes factor, we provide further finite-sample motivations for its use. Connections and comparisons to other automatic methods are discussed and several issues of robustness with respect to priors and data are considered. Finally, we focus on some open problems in the fractional Bayes factor approach, and outline some possible answers and directions for future research.     

Does Equal Pay Legislation Reduce Labour Market Inequality?

This paper considers a labour market model of monopsonistic competition with taste-based discrimination against minority workers to study the effect of equal pay legislation on labour market inequality. When the taste for discrimination is small or competition is weak, the policy removes job segregation and the wage gap completely. However, with a bigger taste for discrimination or stronger competition, equal pay legislation leads to more job segregation, and sometimes minority workers end up earning less than before. Profits of discriminating firms might increase, and discrimination can persist in the long run, although it would have disappeared without the policy.     

A geographic analysis of constituents’ formal participation in the process of international accounting standard setting: Do we have a level playing field?

As a private organization, input legitimacy, being achieved when inputs received reflect the opinions of all stakeholders involved, is a key issue for the IASB’s acceptance as global standard setter. To study this input legitimacy, this paper examines the evolution of constituent participation in international accounting standard setting in terms of geographic diversity over the period 1995–2007 and examines whether biases (due to differences in institutional regimes) or unequal access (due to differences in participation costs) are present in this process. Based on an analysis of 7442 comment letters we observe an increase in participation over time. However, we also find distortions in the geographic representation of constituents, due to differences in the institutional regimes of countries and due to differences in participation costs, proxied by the level of familiarity with the accounting values embedded in IFRS, with the system of private standard setting, and with the English language. These geographic biases in constituent participation might induce criticism in relation to the input legitimacy of the international accounting standard setting process.     

Can a Wealthy Economy Gain from an EU Membership? Adjustment Costs and Long Term Welfare Effects of Full Integration—The Norwegian Case

We employ a large scale macroeconometric model to study adjustment problems and long term welfare effects of a Norwegian EU-membership. Accession costs depend significantly on the country's level of GDP, the size of its agricultural sector and tariff and VAT revenues as these elements determine the net membership contribution. Without the transfers, integrating the economy into EU generates a small welfare gain. This result is strongly affected by a long period with under-utilisation of resources. With the net contribution included, we identify a welfare loss. This is especially so if fiscal policy is changed to maintain the public sector budgetary balance.     

What Do Current Account Reversals in OECD Countries Tell Us About the US Case?

This study examines macroeconomic developments around reversals in current account deficits in 29 OECD countries over four decades and draws some inferences for the present US deficit. Estimates of a probit model indicate that the deepness of the deficit itself, absence of spare production capacity and a beginning real depreciation are factors that increase the likelihood of a current account reversal in the following year. For the US each of these three indicators of a reversal are now on, making a near reversal probable. Over the past 40 years half of the current account deficit reversals in the OECD area were followed by a recession in the countries concerned.