Search results for "jel:C1"

Validation procedures in radiological diagnostic models. Neural network and logistic regression

1999

The objective of this paper is to compare the performance of two predictive radiological models, logistic regression (LR) and neural network (NN), with five different resampling methods. One hundred and sixty-seven patients with proven calvarial lesions as the only known disease were enrolled. Clinical and CT data were used for LR and NN models. Both models were developed with cross validation, leave-one-out and three different bootstrap algorithms. The final results of each model were compared with error rate and the area under receiver operating characteristic curves (Az). The neural network obtained statistically higher Az than LR with cross validation. The remaining resampling validatio…

Economic Returns to Education in France: OLS and Instrumental Variable Estimations

2013

En ligne sur : http://121.52.153.179/JOURNAL/LJE%20VOL%2018-2/Bhatti,%20Bourdon%20and%20Aslam.pdf; International audience; This article estimates the economic returns to schooling as well as analyzing other explanatory factors for the French labor market. It addresses the issue of endogeneity bias and proposes two new instruments for use in the instrumental variable two-stage least squares technique. Our results show that the proposed instruments are relevant and adequate, based on evidence from the available literature. After using the proposed instruments, we find that the OLS coefficients for schooling are biased downwards. Finally, we choose between the two proposed instruments.

Educational Efficiency in a Dea-Bootstrap Approach

2010

We use the PISA 2006 results to analyse the students' proficiencies in 24 European Countries with regard to two indexes that represent the educational resources available at home and the family background of students. Many factors affect the proficiencies and therefore, using a DEA-bootstrap method, we intend to measure the efficiency of the European educational systems as capability to ensure high students' competencies despite adverse conditions about the educational resources available in students' home and the family background.

Assessing Non-Linear Structures in Real Exchange Rates Using Recurrence Plot Strategies

2002

Long-term memories of developed and emerging markets: Using the scaling analysis to characterize their stage of development

2005

The scaling properties encompass in a simple analysis many of the volatility characteristics of financial markets. That is why we use them to probe the different degree of markets development. We empirically study the scaling properties of daily Foreign Exchange rates, Stock Market indices and fixed income instruments by using the generalized Hurst approach. We show that the scaling exponents are associated with characteristics of the specific markets and can be used to differentiate markets in their stage of development. The robustness of the results is tested by both Monte-Carlo studies and a computation of the scaling in the frequency-domain.

Models Used for Measuring Customer Engagement

2013

The purpose of the paper is to define and measure the customer engagement as a forming element of the relationship marketing theory. In the first part of the paper, the authors review the marketing literature regarding the concept of customer engagement and summarize the main models for measuring it. One probability model (Pareto/NBD model) and one parametric model (RFM model) specific for the customer acquisition phase are theoretically detailed. The second part of the paper is an application of the RFM model; the authors demonstrate that there is no statistical significant variation within the clusters formed on two different data sets (training and test set) if the cluster centroids of t…

Multinationals, R&D and productivity: Evidence for UK Manufacturing firms

2010

In this study, we analyze multinationality (domestic-based firms versus multinationals) and foreignness (foreign versus domestic firms) effects in the returns of R&D to productivity. We follow a two-step strategy. In the first step, we consistently estimate firm's productivity by GMM and numerically compute the sample distribution of the R&D returns. In the second step, we use stochastic dominance techniques to make inferences on the multinationality and foreignness effects. Results for a panel of UK manufacturing firms suggest that multinationality and foreignness effects operate in an opposite way: whilst the multinationality effect enhances R&D returns, the foreignness diminishes them. C…

Common functional component modelling

2005

Functional data analysis (FDA) has become a popular technique in applied statistics. In particular, this methodology has received considerable attention in recent studies in empirical finance. In this talk we discuss selected topics of functional principal components analysis that are motivated by financial data.

Organizational Wellness Modeling

2009

The aim of the present paper is to establish certain mathematical models for organizational wellness as well as to create some wellness optimization problems applicable to any type of organization (including universities) that might be mathematically solved resorting to aspects of operational research of mathematical analysis. The results obtained associated with a mathematical apparatus enable one to perform analyses, comparisons, interpretations, predictions. All of us have, consciously or not, a genuine curiosity in creating and shaping organizational wellness. This concept represents a highly topical issue since professional activity, irrespective of its field, holds a very significant …

Partnership formation and dissolution over the life course: applying sequence analysis and event history analysis in the study of recurrent events

2015

We present two types of approach to the analysis of recurrent events for discretely measured data, and show how these methods can complement each other when analysing co-residential partnership histories. Sequence analysis is a descriptive tool that gives an overall picture of the data and helps to find typical and atypical patterns in histories. Event history analysis is used to make conclusions about the effects of covariates on the timing and duration of the partnerships. As a substantive question, we studied how family background and childhood socio-emotional characteristics were related to later partnership formation and stability in a Finnish cohort born in 1959. We found that high se…