Data driven rank test for the change point problem

Data driven test procedure for detection of change is introduced and its properties are studied. The new solution is max-type statistic related to data-driven rank tests for two-sample subproblems. Simulations show that the new test possesses high and stable power. The test is consistent at essentially any alternative. Asymptotic null distribution of the test is derived. The work of the first two authors has been partially supported by the grants GAČR 201/06/0186 and MSM 02160839.     

Measurement of Variables Involved in the Design of a Training Study: Practical Experience Undertaken in a Sports Organisation

This article describes the process for preparing a survey, which will be used to measure relevant variables, which are involved in a study of training needs in a Spanish sports organisation. The variables which have been considered are: problems and difficulties in carrying work of specific positions; “strong points” in carrying out this work; usefulness of the training received in facing and solving the above-mentioned problems and difficulties; usefulness of the training received in acquiring and strengthening these “strong points” in carrying out work; opinion and suggestions with respect to future training. Due to the applied nature of the study, a data collection methodology was designed which was based on interviews and group discussions with a representative sample of workers. Finally, the predictive capacity of perception, which workers have, of their motivation at work was clearly shown in order to then identify different attitude and conduct patterns.     

Extracting Nonlinear Signals from Several Economic Indicators

We develop a twofold analysis of how the information provided by several economic indicators can be used in Markov switching dynamic factor models to identify the business cycle turning points. First, we compare the performance of a fully nonlinear multivariate specification (one‐step approach) with the ‘shortcut’ of using a linear factor model to obtain a coincident indicator, which is then used to compute the Markov switching probabilities (two‐step approach). Second, we examine the role of increasing the number of indicators. Our results suggest that one step is generally preferred to two steps, especially in the vicinity of turning points, although its gains diminish as the quality of the indicators increases. Additionally, we also obtain decreasing returns of adding more indicators with similar signal‐to‐noise ratios. Using the four constituent series of the Stock–Watson coincident index, we illustrate these results for US data. Copyright © 2014 John Wiley & Sons, Ltd.     

Numerical issues in threshold autoregressive modeling of time series

This paper analyses the contribution of various numerical approaches to making the estimation of threshold autoregressive time series more efficient. It relies on the computational advantages of QR factorizations and proposes Givens transformations to update these factors for sequential LS problems. By showing that the residual sum of squares is a continuous rational function over threshold intervals it develops a new fitting method based on rational interpolation and the standard necessary optimality condition. Taking as benchmark a simple grid search, the paper illustrates via Monte Carlo simulations the efficiency gains of the proposed tools.     

Sequential coding of maternal sensitivity: application of nonlinear dynamic analyses and reliability

Quality & Quantity - In infant development, maternal sensitivity is a central construct in the study of the processes involved in the caregiver-infant relationship and child attachment. The...     

An evolutionary approach to the delimitation of labour market areas: an empirical application for Chile

An evolutionary approach to the delimitation of labour market areas: an empirical application for Chile. Spatial Economic Analysis. Labour market areas (LMAs) are argued to represent a more appropriate policy framework than administrative units for the analysis of spatial labour market activity. This article develops LMAs for Chile by applying an evolutionary computation approach. This innovative approach defines LMAs through an optimization process by maximization of internal cohesion, subject to restrictions of minimum levels of self-containment and population. To evaluate the appropriateness of the LMAs, comparative analyses are performed between alternative delimitations based on different parameter configurations of the proposed method versus administrative boundaries and the most widely used method for official LMA delimitation, the travel-to-work areas method.     

Measuring Corporate Environmental Performance: A Methodology for Sustainable Development

Assessing corporate environmental performance (CEP) that is both comprehensive and consistent with sustainable development both for society and companies, while at the same time taking heed of the facts and interests of each stakeholder, is not a simple feat. Due to the multidimensional character of the sustainability concept, several questions must be considered in the evaluation process: (i) the qualitative nature of indicators and the complexity of developing a synthetic index; (ii) the difficulty of choosing properly statistical techniques for aggregation and (iii) the difficulty of introducing stakeholders’ preferences in the assessment models. This paper is an attempt to address this challenge by developing a framework for the assessment of CEP, based on the application of a fuzzy multi‐criterion decision‐making (MCDM) method. To achieve positive scores in a CEP assessment, an organization should be strategically committed and engage in environmental management and governance structures that are translated into good results in terms of both engagement and operational performance. Unless such premises are explicitly incorporated into the assessment criteria, the results would reveal that the CEP measurement could not be brought into a line with an earnest ambition of achieving true sustainable development. Copyright © 2015 John Wiley & Sons, Ltd and ERP Environment     

The Geography of Innovation in China and India

The BRICS countries in general, and China and India in particular, are now widely regarded as the areas of the world likely to challenge the economic leadership of the United States (US) and the European Union (EU). A large part of this challenge will come from rapid technological catch‐up by China and India. Yet, despite a recent rise in interest, there is limited knowledge about how and where innovation takes place in these two leading emerging countries and to what extent the Chinese and Indian territorial systems of innovation differ from those in the EU or the US. In this article we explore the geography of innovation in China and India, concentrating on understanding key territorial‐level innovation trends by country, region and technology field, using the US and the EU as benchmarks. We find significant contrasts between the geography of innovation in China and India and that of the US and the EU. First, the degree of concentration of innovative activities in both countries is extremely high. Levels of agglomeration of innovation in the coastal provinces of China, as well as in Delhi and the South of India, significantly exceed the levels of agglomeration found in the USA and the EU. Secondly, China has witnessed a more rapid increase in the degree of concentration of innovation than India. We posit that the differences in the geography of innovation between, on the one hand, China and India and, on the other hand, between these countries and the developed world are rooted in different institutional settings, different systems of innovation and different national innovation strategies.