Three Bartlett-type corrections for score statistics in symmetric nonlinear regression models

We present simple matrix formulae for corrected score statistics in symmetric nonlinear regression models. The corrected score statistics follow more closely a χ ² distribution than the classical score statistic. Our simulation results indicate that the corrected score tests display smaller size distortions than the original score test. We also compare the sizes and the powers of the corrected score tests with bootstrap-based score tests.     

A sequential approach to testing seasonal unit roots in high frequency data

In this paper we introduce a sequential seasonal unit root testing approach which explicitly addresses its application to high frequency data. The main idea is to see which unit roots at higher frequency data can also be found in temporally aggregated data. We illustrate our procedure to the analysis of monthly data, and we find, upon analysing the aggregated quarterly data, that a smaller amount of test statistics can sometimes be considered. Monte Carlo simulation and empirical illustrations emphasize the practical relevance of our method.     

Bayesian inverse problems with heterogeneous variance

We consider inverse problems in Hilbert spaces under correlated Gaussian noise, and use a Bayesian approach to find their regularized solution. We focus on mildly ill-posed inverse problems with fractional noise, using a novel wavelet-based vaguelette–vaguelette approach. It allows us to apply sequence space methods without assuming that all operators are simultaneously diagonalizable. The results are proved for more general bases and covariance operators. Our primary aim is to study posterior contraction rate in such inverse problems over Sobolev classes and compare it to the derived minimax rate. Secondly, we study effect of plugging in a consistent estimator of variances in sequence space on the posterior contraction rate. This result is applied to the problem with error in forward operator. Thirdly, we show that empirical Bayes posterior distribution with a plugged-in maximum marginal likelihood estimator of the prior scale contracts at the optimal rate, adaptively, in the minimax sense.     

The making of ‘Brother Time’: extending a traditional project through visual methods

Previously interested on how the Internet was shaping science in less developed regions, the World Science Project turned its research lenses to document the often-tragic setting of science in less developed regions. Based upon 100 hours of video documentation and extensive interviews (conducted in 2008 and 2009) with Kenyan research professionals, university administrators, religious leaders, journalists, shopkeepers, farmers, college students, and internally displaced refugees, our international research team investigated the unique role played by universities and research institutes during a violent political episode following presidential elections. Conducting video research that focuses on a sensitive political issue in a developing nation, involves a variety of logistical, cultural, and methodological obstacles that continued through post-production. Despite these challenges, the video documentary dimension of the research project proved instrumental in (1) reflecting upon, as well as extending, our empirical research on science in less developed regions and, as importantly, (2) elaborating upon a theoretical perspective that has evolved out of this research – Re-agency.     

A Task-Based Indicator for Labour Market Mismatch

This article uses a task-based approach to measure labour market mismatch and to study the wage effects of mismatch. We propose a new indicator—cognitive mismatch—and contrast it with the commonly used overqualification indicator. We argue that considering the tasks performed in each occupation captures more adequately the complexity of job requirements and tackles the major drawbacks of the existing approaches measuring mismatch. Using rich administrative data from the German Sample of Integrated Labour Market Biographies, we find that 4.8% of the total employment episodes are matched in terms of qualification but mismatched in terms of the tasks performed. Fixed Effects models show that the largest wage loss occurs in cases of mismatch in both education level and tasks performed at work. We conclude that each indicator is capturing different facets of mismatch and that they should be used complementarily in labour market mismatch analyses.

     

Population Structure and the Human Development Index

Social Indicators Research - This paper provides an alternative way of measuring human development that takes explicitly into account the differences in the countries’ population structures....