Statistical tests for multiple forecast comparison

We consider a multivariate version of the Diebold–Mariano test for equal predictive ability of three or more forecasting models. The Wald-type test, $S$, which has a null distribution that is asymptotically chi-squared, is shown to be generally invariant with respect to the ordering of the models being compared. Finite-sample corrections for the test are also developed. Monte Carlo simulations indicate that $S$ has reasonable size properties in large samples but tends to be oversized in moderate samples. The finite-sample correction succeeds in correcting for size, but only partially. For the size-adjusted tests, power increases with sample size, as expected. It is speculated that further finite-sample improvements can be achieved using Hotelling’s $T^2$ or bootstrap critical values.     

First steps towards cross-national transfer in integrating mobility management and land use planning in the EU and Switzerland

This paper is based on research carried out in an EU Framework project, concerning the better integration of mobility management (MM) with land use planning. The objective of the paper is to analyse how, and how far, policies in this field of action can transfer from one member state to another, and to compare this to the theory of policy transfer put forward by Dolowitz and Marsh (2000), using their theory as an analytical framework, but also informing that theory. After providing a definition of this form of integration, the paper explains how far MM and land use planning are currently integrated in the EU member and other states covered in the research (Sweden, Germany, Spain, Lithuania, Poland, Slovenia, Switzerland, the UK, as well as Ireland and the Netherlands). It then presents the results of planning simulation workshops in five of these countries, where a group of planning professionals from each state considered real development sites and how MM could be integrated with the development. It shows that there is scope for transfer but concludes that barriers such as language, differing planning traditions, and the problem of transferring a new policy idea within a country will limit the scope of policy transfer significantly. Nonetheless, it sees a role for EU projects of this nature in encouraging initial consideration of new policy ideas.     

Social capital effects on the discovery and exploitation of entrepreneurial opportunities

Social capital refers to social networks and the norms of reciprocity, cooperation and trust associated with them. It can be studied at different levels of analysis. As previous literature suggests, social capital has aspects at both the individual and collective levels. However, theory development and empirical research have focused on separate, sometimes diverging levels. In an attempt to address this, this research examines the simultaneous influence of individual and regional social capital on the discovery and exploitation of entrepreneurial opportunities using individual-level data from the Global Entrepreneurship Monitor linked with regional-level data on social capital. The results show that individuals from regions with higher social capital are more likely to discover and to exploit entrepreneurial opportunities. Moreover, individuals having networks with other entrepreneurs are also more likely to identify a business opportunity and to become an entrepreneur. Also, we found that social capital at individual level had a greater effect than social capital at regional level in the two stages of the entrepreneurial process.     

Intergovernmental transfers and fiscal behavior insurance versus aggregate discipline

This paper evaluates the trade-off between the advantages of risk sharing and the perils of common pool problems in federal fiscal arrangements. Under the assumption of asymmetric information we evaluate two alternative regimes of intergovernmental transfers. In one regime, the central government pre-commits to a certain level of transfers that compensate vertical fiscal imbalances and provide some limited ex-ante insurance. In the other regime, it accommodates ex-post the fiscal needs of the different provinces. In this second case, full-insurance results, but the economy is subject to a tragedy of the fiscal commons, with excessive subnational spending, insufficient local taxation, and reduced production of federal public goods. We find the range of parameters for which one or the other institutional regime will be preferable. The result is a fiscal-federalism version of the usual trade-off between rules and discretion.     

Changing Patterns of Precipitation at the Sooke Reservoir in British Columbia

The paper is a parametric and nonparametric analysis of past precipitation data. We analyze 90 years of daily precipitation data at the Sooke Reservoir in British Columbia, Canada, for evidence of climate change. We fit probability density functions (PDFs) to the data and find evidence of a structural break in the data generating process by using the Andrews-Ploberger test. To confirm this finding, we analyze higher moments of the distribution of precipitation and show that the PDFs have become more leptokurtic. The results show how the pattern of precipitation has changed.     

Sequencing of Economic Reforms in the Presence of Political Constraints

This paper presents a model portraying a country in a political deadlock about economic reform proposals in which certain measures hurt strongly-organized interests. We show that when governments are unable to precommit and interest groups have veto power, only far-reaching reforms (even if quite costly) have hope of success. The model intends to explain why in recent years several Latin American countries have opted for radical reform.