Empirical Evidence of the Distributional Effects of the CAP in the New EU Member States. Factor Markets Working Document No. 58, August 2013

This study, carried out in the context of the Factor Markets research project, investigates the impact of the SAPS (Single Area Payment Scheme) on farmland rental rates in the new EU member states. Using a unique set of farm level panel data with 20,930 observations for 2004 and 2005 we are able to control for important sources of endogeneity. According to our results, the SAPS has a positive and statistically significant impact on land rents in the EU. However, the estimated incidence is smaller than predicted theoretically. Land rents capture only 19 cents of the marginal SAPS euro, and around 10% of the SAPS benefit non-farming landowners through higher farmland rental prices. As the share of rented land is higher in corporate farms than individual ones, family farms benefit more from the SAPS than corporate farms do.

Is socioeconomic position early in life associated with physical activity during adulthood following the accumulation of risk model with additive effects?

L'activité physique améliore la santé, mais seulement 4.8% des Canadiens atteignent le niveau recommandé. La position socio-économique est un des déterminants de l'activité physique les plus importants. Elle est associée à l’activité physique de manière transversale à l’adolescence et à l’âge adulte. Cette thèse a tenté de déterminer s'il y a une association à long terme entre la position socio-économique au début du parcours de vie et l’activité physique à l’âge adulte. S'il y en avait une, un deuxième objectif était de déterminer quel modèle théorique en épidémiologie des parcours de vie décrivait le mieux sa forme. Cette thèse comprend trois articles: une recension systématique et deux recherches originales. Dans la recension systématique, des recherches ont été faites dans Medline et EMBASE pour trouver les études ayant mesuré la position socio-économique avant l'âge de 18 ans et l'activité physique à ≥18 ans. Dans les deux recherches originales, la modélisation par équations structurelles a été utilisée pour comparer trois modèles alternatifs en épidémiologie des parcours de vie: le modèle d’accumulation de risque avec effets additifs, le modèle d’accumulation de risque avec effet déclenché et le modèle de période critique. Ces modèles ont été comparés dans deux cohortes prospectives représentatives à l'échelle nationale: la 1970 British birth cohort (n=16,571; première recherche) et l’Enquête longitudinale nationale sur les enfants et les jeunes (n=16,903; deuxième recherche). Dans la recension systématique, 10 619 articles ont été passés en revue par deux chercheurs indépendants et 42 ont été retenus. Pour le résultat «activité physique» (tous types et mesures confondus), une association significative avec la position socio-économique durant l’enfance fut trouvée dans 26/42 études (61,9%). Quand seulement l’activité physique durant les loisirs a été considérée, une association significative fut trouvée dans 21/31 études (67,7%). Dans un sous-échantillon de 21 études ayant une méthodologie plus forte, les proportions d’études ayant trouvé une association furent plus hautes : 15/21 (71,4%) pour tous les types et toutes les mesures d’activité physique et 12/15 (80%) pour l’activité physique de loisir seulement. Dans notre première recherche originale sur les données de la British birth cohort, pour la classe sociale, nous avons trouvé que le modèle d’accumulation de risque avec effets additifs s’est ajusté le mieux chez les hommes et les femmes pour l’activité physique de loisir, au travail et durant les transports. Dans notre deuxième recherche originale sur les données canadiennes sur l'activité physique de loisir, nous avons trouvé que chez les hommes, le modèle de période critique s’est ajusté le mieux aux données pour le niveau d’éducation et le revenu, alors que chez les femmes, le modèle d’accumulation de risque avec effets additifs s’est ajusté le mieux pour le revenu, tandis que le niveau d’éducation ne s’est ajusté à aucun des modèles testés. En conclusion, notre recension systématique indique que la position socio-économique au début du parcours de vie est associée à la pratique d'activité physique à l'âge adulte. Les résultats de nos deux recherches originales suggèrent un patron d’associations le mieux représenté par le modèle d’accumulation de risque avec effets additifs.

A Mixture model with random-effects components for clustering correlated gene-expression profiles

Motivation: The clustering of gene profiles across some experimental conditions of interest contributes significantly to the elucidation of unknown gene function, the validation of gene discoveries and the interpretation of biological processes. However, this clustering problem is not straightforward as the profiles of the genes are not all independently distributed and the expression levels may have been obtained from an experimental design involving replicated arrays. Ignoring the dependence between the gene profiles and the structure of the replicated data can result in important sources of variability in the experiments being overlooked in the analysis, with the consequent possibility of misleading inferences being made. We propose a random-effects model that provides a unified approach to the clustering of genes with correlated expression levels measured in a wide variety of experimental situations. Our model is an extension of the normal mixture model to account for the correlations between the gene profiles and to enable covariate information to be incorporated into the clustering process. Hence the model is applicable to longitudinal studies with or without replication, for example, time-course experiments by using time as a covariate, and to cross-sectional experiments by using categorical covariates to represent the different experimental classes. Results: We show that our random-effects model can be fitted by maximum likelihood via the EM algorithm for which the E(expectation) and M(maximization) steps can be implemented in closed form. Hence our model can be fitted deterministically without the need for time-consuming Monte Carlo approximations. The effectiveness of our model-based procedure for the clustering of correlated gene profiles is demonstrated on three real datasets, representing typical microarray experimental designs, covering time-course, repeated-measurement and cross-sectional data. In these examples, relevant clusters of the genes are obtained, which are supported by existing gene-function annotation. A synthetic dataset is considered too.

Multi-level zero-inflated Poisson regression modelling of correlated count data with excess zeros

Count data with excess zeros relative to a Poisson distribution are common in many biomedical applications. A popular approach to the analysis of such data is to use a zero-inflated Poisson (ZIP) regression model. Often, because of the hierarchical Study design or the data collection procedure, zero-inflation and lack of independence may occur simultaneously, which tender the standard ZIP model inadequate. To account for the preponderance of zero counts and the inherent correlation of observations, a class of multi-level ZIP regression model with random effects is presented. Model fitting is facilitated using an expectation-maximization algorithm, whereas variance components are estimated via residual maximum likelihood estimating equations. A score test for zero-inflation is also presented. The multi-level ZIP model is then generalized to cope with a more complex correlation structure. Application to the analysis of correlated count data from a longitudinal infant feeding study illustrates the usefulness of the approach.

Constructing internationally comparable real income aggregates by combining sparse benchmark data with annual national accounts data: A state-space approach

The importance of availability of comparable real income aggregates and their components to applied economic research is highlighted by the popularity of the Penn World Tables. Any methodology designed to achieve such a task requires the combination of data from several sources. The first is purchasing power parities (PPP) data available from the International Comparisons Project roughly every five years since the 1970s. The second is national level data on a range of variables that explain the behaviour of the ratio of PPP to market exchange rates. The final source of data is the national accounts publications of different countries which include estimates of gross domestic product and various price deflators. In this paper we present a method to construct a consistent panel of comparable real incomes by specifying the problem in state-space form. We present our completed work as well as briefly indicate our work in progress.

Wage inequality and the role of multinationals:evidence from UK panel data

Despite the increased attention on the impacts of globalisation, there has been little empirical investigation into the impact of multinational firms on the domestic labour market and in particular wage inequality, this is in spite of a rapid increase in foreign direct investment (FDI) at around the same time of rising inequality. Using UK panel data, this paper tests whether inward flows of FDI have contributed to increasing wage inequality. Even after controlling for the two most common explanations of wage inequality, technology and trade, we find that FDI has a significant effect upon wage inequality, with the overall impact of FDI explaining on average 11% of wage inequality. © 2003 Elsevier B.V. All rights reserved.

Combining temporal and spectral information with spatial mapping to identify differences between phonological and semantic networks:a magnetoencephalographic approach

Early, lesion-based models of language processing suggested that semantic and phonological processes are associated with distinct temporal and parietal regions respectively, with frontal areas more indirectly involved. Contemporary spatial brain mapping techniques have not supported such clear-cut segregation, with strong evidence of activation in left temporal areas by both processes and disputed evidence of involvement of frontal areas in both processes. We suggest that combining spatial information with temporal and spectral data may allow a closer scrutiny of the differential involvement of closely overlapping cortical areas in language processing. Using beamforming techniques to analyze magnetoencephalography data, we localized the neuronal substrates underlying primed responses to nouns requiring either phonological or semantic processing, and examined the associated measures of time and frequency in those areas where activation was common to both tasks. Power changes in the beta (14-30 Hz) and gamma (30-50 Hz) frequency bandswere analyzed in pre-selected time windows of 350-550 and 500-700ms In left temporal regions, both tasks elicited power changes in the same time window (350-550 ms), but with different spectral characteristics, low beta (14-20 Hz) for the phonological task and high beta (20-30 Hz) for the semantic task. In frontal areas (BA10), both tasks elicited power changes in the gamma band (30-50 Hz), but in different time windows, 500-700ms for the phonological task and 350-550ms for the semantic task. In the left inferior parietal area (BA40), both tasks elicited changes in the 20-30 Hz beta frequency band but in different time windows, 350-550ms for the phonological task and 500-700ms for the semantic task. Our findings suggest that, where spatial measures may indicate overlapping areas of involvement, additional beamforming techniques can demonstrate differential activation in time and frequency domains. © 2012 McNab, Hillebrand, Swithenby and Rippon.

A comparison of sales response predictions from demand models applied to store-level versus panel data

In order to generate sales promotion response predictions, marketing analysts estimate demand models using either disaggregated (consumer-level) or aggregated (store-level) scanner data. Comparison of predictions from these demand models is complicated by the fact that models may accommodate different forms of consumer heterogeneity depending on the level of data aggregation. This study shows via simulation that demand models with various heterogeneity specifications do not produce more accurate sales response predictions than a homogeneous demand model applied to store-level data, with one major exception: a random coefficients model designed to capture within-store heterogeneity using store-level data produced significantly more accurate sales response predictions (as well as better fit) compared to other model specifications. An empirical application to the paper towel product category adds additional insights. This article has supplementary material online.

Inherited labour hoarding, insiders and employment growth:panel data results : Poland, 1996-2002

Using panel data pertaining to large Polish (non-financial) firms this paper examines the determinants of employment change during the period 1996-2002. Paying particular attention to the asymmetry hypothesis we investigate the impact of own wages, outside wages, output growth, regional characteristics and sectoral affiliation on the evolution of employment. In keeping with the 'right to manage' model we find that employment dynamics are not affected negatively by alternative wages. Furthermore, in contrast to the early transition period, we find evidence that employment levels respond to positive sales growth (in all but state firms). The early literature, (e.g. Kollo, 1998) found that labour hoarding lowered employment elasticities in the presence of positive demand shocks. Our findings suggest that inherited labour hoarding may no longer be a factor. We argue that the present pattern of employment adjustment is better explained by the role of insiders. This tentative conclusion is hinged on the contrasting behaviour of state and privatised companies and the similar behaviour of privatised and new private companies. We conclude that lower responsiveness of employment to both positive and negative changes in revenue in state firms is consistent with the proposition that rent sharing by insiders is stronger in the state sector.

Is socioeconomic position early in life associated with physical activity during adulthood following the accumulation of risk model with additive effects?

L'activité physique améliore la santé, mais seulement 4.8% des Canadiens atteignent le niveau recommandé. La position socio-économique est un des déterminants de l'activité physique les plus importants. Elle est associée à l’activité physique de manière transversale à l’adolescence et à l’âge adulte. Cette thèse a tenté de déterminer s'il y a une association à long terme entre la position socio-économique au début du parcours de vie et l’activité physique à l’âge adulte. S'il y en avait une, un deuxième objectif était de déterminer quel modèle théorique en épidémiologie des parcours de vie décrivait le mieux sa forme. Cette thèse comprend trois articles: une recension systématique et deux recherches originales. Dans la recension systématique, des recherches ont été faites dans Medline et EMBASE pour trouver les études ayant mesuré la position socio-économique avant l'âge de 18 ans et l'activité physique à ≥18 ans. Dans les deux recherches originales, la modélisation par équations structurelles a été utilisée pour comparer trois modèles alternatifs en épidémiologie des parcours de vie: le modèle d’accumulation de risque avec effets additifs, le modèle d’accumulation de risque avec effet déclenché et le modèle de période critique. Ces modèles ont été comparés dans deux cohortes prospectives représentatives à l'échelle nationale: la 1970 British birth cohort (n=16,571; première recherche) et l’Enquête longitudinale nationale sur les enfants et les jeunes (n=16,903; deuxième recherche). Dans la recension systématique, 10 619 articles ont été passés en revue par deux chercheurs indépendants et 42 ont été retenus. Pour le résultat «activité physique» (tous types et mesures confondus), une association significative avec la position socio-économique durant l’enfance fut trouvée dans 26/42 études (61,9%). Quand seulement l’activité physique durant les loisirs a été considérée, une association significative fut trouvée dans 21/31 études (67,7%). Dans un sous-échantillon de 21 études ayant une méthodologie plus forte, les proportions d’études ayant trouvé une association furent plus hautes : 15/21 (71,4%) pour tous les types et toutes les mesures d’activité physique et 12/15 (80%) pour l’activité physique de loisir seulement. Dans notre première recherche originale sur les données de la British birth cohort, pour la classe sociale, nous avons trouvé que le modèle d’accumulation de risque avec effets additifs s’est ajusté le mieux chez les hommes et les femmes pour l’activité physique de loisir, au travail et durant les transports. Dans notre deuxième recherche originale sur les données canadiennes sur l'activité physique de loisir, nous avons trouvé que chez les hommes, le modèle de période critique s’est ajusté le mieux aux données pour le niveau d’éducation et le revenu, alors que chez les femmes, le modèle d’accumulation de risque avec effets additifs s’est ajusté le mieux pour le revenu, tandis que le niveau d’éducation ne s’est ajusté à aucun des modèles testés. En conclusion, notre recension systématique indique que la position socio-économique au début du parcours de vie est associée à la pratique d'activité physique à l'âge adulte. Les résultats de nos deux recherches originales suggèrent un patron d’associations le mieux représenté par le modèle d’accumulation de risque avec effets additifs.

Performance determinants For Swedish Financial Monetary Institutions: Panel Data evidence between 2010-2014.

Due to the rapid changes that governs the Swedish financial sector such as financial deregulations and technological innovations, it is imperative to examine the extent to which the Swedish Financial institutions had performed amid these changes. For this to be accomplish, the work investigates what are the determinants of performance for Swedish Financial Monetary Institutions? Assumptions were derived from theoretical and empirical literatures to investigate the authenticity of this research question using seven explanatory variables. Two models were specified using Returns on Asset (ROA) and Return on Equity (ROE) as the main performance indicators and for the sake of reliability and validity, three different estimators such as Ordinary Least Square (OLS), Generalized Least Square (GLS) and Feasible Generalized Least Square (FGLS) were employed. The Akaike Information Criterion (AIC) was also used to verify which specification explains performance better while performing robustness check of parameter estimates was done by correcting for standard errors. Based on the findings, ROA specification proves to have the lowest Akaike Information Criterion (AIC) and Standard errors compared to ROE specification. Under ROA, two variables; the profit margins and the Interest coverage ratio proves to be statistically significant while under ROE just the interest coverage ratio (ICR) for all the estimators proves significant. The result also shows that the FGLS is the most efficient estimator, then follows the GLS and the last OLS. when corrected for SE robust, the gearing ratio which measures the capital structure becomes significant under ROA and its estimate become positive under ROE robust. Conclusions were drawn that, within the period of study three variables (ICR, profit margins and gearing) shows significant and four variables were insignificant. The overall findings show that the institutions strive to their best to maximize returns but these returns were just normal to cover their costs of operation. Much should be done as per the ASC theory to avoid liquidity and credit risks problems. Again, estimated values of ICR and profit margins shows that a considerable amount of efforts with sound financial policies are required to increase performance by one percentage point. Areas of further research could be how the individual stochastic factors such as the Dupont model, repo rates, inflation, GDP etc. can influence performance.

The Influence of Age and Size on Family-Owned Firms’ Financing Decisions: Empirical Evidence Using Panel Data

Based on four samples of Portuguese family-owned firmsdi) 185 young, low-sized family-owned firms; ii) 167 young, high-sized familyowned firms; iii) 301 old, low-sized family-owned firms; and iv) 353 old, high-sized family-owned firms d we show that age and size are fundamental characteristics in family-owned firms’ financing decisions. The multiple empirical evidence obtained allows us to conclude that the financing decisions of young, low-sized family-owned firms are quite close to the assumptions of Pecking Order Theory, whereas those of old, high-sized family-owned firms are quite close to what is forecast by Trade-Off Theory. The lesser information asymmetry associated with greater age, the lesser likelihood of bankruptcy associated with greater size, as well as the lesser concentration of ownership and management consequence of greater age and size, may be especially important in the financing decisions of family-owned firms. In addition, we find that GDP, interest rate and periods of crisis have a greater effect on the debt of young, low-sized family-owned firms than on that of family-owned firms of the remainder research samples.

Assessing influence in survival data with a cure fraction and covariates

Diagnostic methods have been an important tool in regression analysis to detect anomalies, such as departures from error assumptions and the presence of outliers and influential observations with the fitted models. Assuming censored data, we considered a classical analysis and Bayesian analysis assuming no informative priors for the parameters of the model with a cure fraction. A Bayesian approach was considered by using Markov Chain Monte Carlo Methods with Metropolis-Hasting algorithms steps to obtain the posterior summaries of interest. Some influence methods, such as the local influence, total local influence of an individual, local influence on predictions and generalized leverage were derived, analyzed and discussed in survival data with a cure fraction and covariates. The relevance of the approach was illustrated with a real data set, where it is shown that, by removing the most influential observations, the decision about which model best fits the data is changed.

Fitting a mixture model to three-mode three-way data with missing information

When the data consist of certain attributes measured on the same set of items in different situations, they would be described as a three-mode three-way array. A mixture likelihood approach can be implemented to cluster the items (i.e., one of the modes) on the basis of both of the other modes simultaneously (i.e,, the attributes measured in different situations). In this paper, it is shown that this approach can be extended to handle three-mode three-way arrays where some of the data values are missing at random in the sense of Little and Rubin (1987). The methodology is illustrated by clustering the genotypes in a three-way soybean data set where various attributes were measured on genotypes grown in several environments.

On clustering interval data with different scales of measures : experimental results

This article is is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. Attribution-NonCommercial (CC BY-NC) license lets others remix, tweak, and build upon work non-commercially, and although the new works must also acknowledge & be non-commercial.