ECONOMETRICS

Author: BROTO PELEGRIN CARMEN.
Year: 2003.
University: CARLOS III DE MADRID [More theses of this university] [www.uc3m.es].
Place of defense: FACULTAD DE CIENCIAS SOCIALES Y JURIDICAS.
Place of preparation: UNIVERSIDAD CARLOS III DE MADRID.

Summary: In this thesis discusses some aspects relevant to the analysis of time series conditionally heterocedásticas. First, it makes a detailed review of the methods of estimating models stochastic volatility (SV), whose properties, comparative advantages and disadvantages had not been discussed recently. Different methods are illustrated with simulated data and an application to yield empirical daily S & P 500. He then proposes a new model components inobservados and disturbances conditionally heterocedásticas type asymmetric. It believes that the series is a model of random walk more noise, whose innovations still processes GQARCH (1.1). After analyzing the statistical properties of the model, however, comes the asymptotic distribution and some properties of finite samples estimator PMV. Finally, it is proposed the use of correlations of the squares of waste assistants to detect the presence of heterocedasticidad in cualquier.componente and presents empirical applications of the model to a series of financial and prices. Finally generalises the model by incorporating a component seasonal homocedástico, which can be deterministic or stochastic. Analizadas properties of the estimators in finite sample, it fits the model of eight rounds of inflation.

Author: ROSOLIA ALFONSO.
Year: 2004.
University: POMPEU FABRA [More theses of this university] [www.upf.edu].
Place of defense: DEPARTAMENTO DE ECONOMÍA Y EMPRESA.
Place of preparation: DEPARTAMENTO DE ECONOMÍA Y EMPRESA.

Summary: Over the last ten years, economists have recognized that in many cases the individual choices are affected by the decisions, behavioral preferences of other players not only through market but also directly by imitation or learning, development social rules shared by the dissemination of information. Many studies have examined these mechanisms in several contexts. Among other highlights education, the labor market, criminality, habitudines health. The significance of these effects of neighborhood is positive and regulations at the same time. On the one hand, their existence contributes to the understanding of the extreme variability of economic phenomena among some groups of individuals apparently homogeneous. On the other hand, their existence is a key component for the development of effective interventions by the policy maker. Studies of the thesis discusses these effects in the context of decisions esscolares and in the labor market. The first chapter shows the decision and success in completing secondary education by adolescent males positively affects the women of the same age living in the same cities. The sample used campionaria allows conlcuir that the correlation between the success of the men and women actually corresponds to a causal relationship between the two variables. It is concluded that any intervention that would increase the likelihood of completing secondary studies for males of one percent as a consequence also will have an increased likelihood of adolescent girls to complete these studies between 0.6 and 0.7 percent. In the second chapter will evaluate the impact on the duration of unemployment belong to a larger social group. Recent work has shown how to be centered around theoretical member of a larger group of individuals can contribute to raising the probability of finding a job when unemployment. However, the evidence so far is empirica low. The research develops measures of the extent and quality of the social group to which he belongs each of the individuals in a sample of workers who lost their jobs because of company closures. Consistent with the impicaciones theoretical, the analysis showed that these effects are statistically significant and negative belong to a larger group or individuals who have more employment reduces the duration of the period of unemployment. The third chapter discusses the consequences on the evolution of the inequality of pay differences between the policies of enterprises. The sample used includes 1500 Italian companies and allows the estimation equations of wages nivèl business over the last 30 years. These are compared with the results of a standard analysis of inequality based on the estimation of a equacion wage common to all businesses. The results show that interpretations based on the standard analysis put more emphasis on the characteristics observable individual and not observable, but our analysis suggests that the role played by the prices of these things is more important what is commonly assumed.

Author: SORDO JUANENA JOSÉ MARÍA.
Year: 2005.
University: COMPLUTENSE DE MADRID [More theses of this university] [www.ucm.es].
Place of defense: FACULTAD DE EDUCACIÓN.
Place of preparation: FACULTAD DE EDUCACIÓN - UNIVERSIDAD COMPLUTENSE DE MADRID.

Summary: That argument makes improvements in the teaching and learning of geometry metrics, also called geometry of the rule and the meter, in the training of teachers in the Primary School of Education. It has used a new teaching strategy with the addition of a program of dynamic geometry as is the "Geometr's Sketchapd." The teaching strategy has two key inputs: on the one hand, there is a new organization to the teaching geometry that is structured on the basis of a theory of building knowledge-type computing, in particular the "Adapive Control of Thought (ACT)" Anderson. Moreover, the incorporation of the "Geometr's Sketchpad" along with the resolution of problem situations and use of the Internet has meant putting into play a new climate of the kind of cooperative.

Author: BREY SÁNCHEZ RAÚL.
Year: 2005.
University: PABLO DE OLAVIDE [More theses of this university] [www.upo.es].
Place of defense: FACULTAD DE CIENCIAS EMPRESARIALES.
Place of preparation: FACULTAD DE EMPRESARIALES.

Summary: The Methods of Preferences Declaradas (MPD) are valuation techniques that are based on decisions made by individuals in marked hypothetical designed by surveys. The Contingent Value Method (MVC) with its various formats elicitaicón has so far been more technique applied in most countries. However, the use of other MPD is reached growing popularity, especially some variants of models Election (MOU) (see, eg Morrison et al., 1996; Hanley et al., 2001; Bateman et al. 2002 for a more deep in the ME and the environmental assessment). In the MOU, are presented to individuals joint election composed of several alternatives with fixed attributes, making them reveal their preferences for alternatives through various tasks. The type of tasks that election requires that individuals perform depends on the precise way elicitaicón employee. The methods that provide more information are those that involve a greater demand cognitive (Louviere et al., 2000), which in practice could affect the reliability of these methods. In this context, this research project proposes a new method elicitaicón preference, we have called Partnership Quota (GA), which attempts to balance both. This method was compared with two other ME: Experiments and Election Management Quota. The comparison is made in terms of efficiency and statistical cognitive demand. The Association contingent can be seen as an alternative method that improves experiments Election collecting more information without imposing some cognitive demands as high as those of the Quota Management.

Author: JAROCINSKI MAREK.
Year: 2005.
University: POMPEU FABRA [More theses of this university] [www.upf.edu].
Place of defense: DEPARTAMENTO DE ECONOMÍA Y EMPRESA.
Place of preparation: UNVIERSIDAD POMPEU FABRA.

Summary: This thesis deals with the problems of econometric estimation with small sample sizes, in the contexts of VARs monetary and empirical research of growth. First, it demonstrates how to improve the VAR structural analysis in the presence of small sample. The first chapter fits with the specification prior interchangeable (exchangeable prior) to the context of the VAR, and obtains new results on the transmission of monetary new members of the European Union. The second chapter proposes a prior growth rates on initial delas variables modeled. This prior is in correcting the bias classic dela small sample in time series and reconciles views on the classical and Bayesian estimation of time-series models. The third chapter examines the impact of the error of measuring national income on empirical results of economic growth, and demonstrates that the procedures econometric robust to uncertainty about the model are highly sensitive to measurement error in the data.

Author: COROMINA SOLER LLUIS.
Year: 2005.
University: GIRONA [More theses of this university] [www.udg.es].
Place of defense: FACULTAD DE ECONÓMICAS.
Place of preparation: UNIVERSITAT DE GIRONA.

Summary: The objective of this thesis is to predict the performance of doctoral students at the University of Girona as personal characteristics (background), attitudinal and social networking for students. The study population are students of third and fourth grade and his doctoral dissertation directors. To obtain the data has designed a website questionnaire specifying their advantages and taking into account some non-traditional problems of coverage and no answer. The questionnaire site was due to the complexity of the questions involving social network. The electronic questionnaire allows, through a series of instructions, reducing the time to respond and make it less loaded. This questionnaire site, it is self-managed, allowing us to, according to the literature, more honest answers to the questionnaire with pollster. It analyzes the quality of the questions in the questionnaire social networking site for data egocentric. For it is estimated that the reliability and validity of such questions, for the first time through the model Multirasgo Multimétodo (Multitrait Multimethod). Being data egocentric, can be considered hierarchical, and for the first time joined a model Multirasgo Multimétodo (multilevel Multitrait Multimethod). The reliability and validity can be obtained at the individual level (within component group) or group level (beetween group component) and are used to conduct a meta-analysis with other European universities to discuss certain design features of the questionnaire. These features discussed whether to queries made in social network Web questionnaires are more reliable and valid made "by questions" or "alters by" if all are present frequency tags for the items or just the beginning and end, or if it is better that the design of the questionnaire to be in color or black and white. It analyzes the quality of the social network as a whole, in this specific case are research groups at the university. It addresses the problems of data absent from the entire networks. It proposes a new alternative to the solution of the typical network or egocentric respondents proxies. This new alternative we have named "Nosduocentered Network (network Nosduocentrada), is based on two central actors in a network. Believing regression models, this "Nosduocentered network" has more predictive power for the performance of doctoral students that the network egocentric. Besides correcting the correlations delas attitudinal variables for attenuation due to the small sample size. Finally, regressions are made of three types of variables (background, attitudinal and social network) and then combine to analyze which to better predict the performance (as academic publications) of doctoral students. The results led us to predict the academic achievement of students in doctoral depends on personal variables (background) i attitudinal. Moreover, the results obtained are compared with other published studies.

Author: COROMINA SOLER LLUIS.
Year: 2005.
University: GIRONA [More theses of this university] [www.udg.es].
Place of defense: FACULTAD DE ECONÓMICAS.
Place of preparation: UNIVERSITAT DE GIRONA.

Summary: The objective of this thesis is to predict the performance of doctoral students at the University of Girona as personal characteristics (background), attitudinal and social networking for students. The population studied in third and fourth grade and his doctoral dissertation directors. To obtain the data has designed a website questionnaire specifying their advantages and taking into account some non-traditional problems of coverage or response. The questionnaire site was due to the complexity of the questions involving social network. The electronic questionnaire allows, through a series of instructions, reducing the time to respond and make it less loaded. This questionnaire site, it is self-managed, allowing us to, according to the literature, as a more honest answers to the questionnaire with pollster. It analyzes the quality of the questions in the questionnaire social networking site for data egocentric. For it is estimated that the reliability and validity of such questions, for the first time through the model Multirasgo Multimétodo (Multitrait Multimethod). Being data egocentric, can be considered hierarchical, and for the first time will receive a Model Multirasgo Multimétodo Layered (multilevel Multitrait Multimethod). The reliability and validity can be obtained at the individual level (withing group component) or group level (between group component) and are used to conduct a meta-analysis with other European universities to discuss certain design features of the questionnaire. These features discussed whether to queries made in social network Web questionnaires are more reliable and valid made "by questions" or "alters by" if all are present frequency tags for the items or just the beginning and end, or if it is better that the design of the questionnaire is in color or black and white. It analyzes the quality of the social network as a whole, in this specific case are research groups at the university. It addresses the problems of data absent from the entire networks. It proposes a new alternative to the solution of the typical network or egocentric respondents proxies. This new alternative we have named "Nosduocentered Network (network Nosduocentrada), is based on two central actors in a network. Believing regression models, this "Nosduocentered noetwork" has more predictive power for the performance of doctoral students that the network egocentric. Besides correcting the correlations of attitudinal variables for attenuation due to the small sample size. Finally, regressions are made of three types of variables (background, attitudinal and social network) and then combine to analyze which predicts better performance (as academic publications) of doctoral students. The results leads us to predict the academic achievement of students in doctoral depends on personal variables (background) i attitudinal. Moreover, the results obtained are compared with other published studies.

Author: Gómez Castillo Nicolás.
Year: 2006.
University: AUTÓNOMA DE BARCELONA [More theses of this university] [www.uab.es].
Place of defense: Dep. d'Economia i d'Historia Econòmica..
Place of preparation: Facultat Econòmiques.

Summary: When forecasting time series variables, it is usual to use only the information provided by past observations to foresee potential future developments. However, if available, additional information should be taken into account to get the forecast. For example, let us consider a case where the Government announces an economic target for next year. Since the Government has the empowerment to implement the economic or social policies to approach the target, an analyst that does not consider this information to get the forecast and makes use only of the historical record of the variables, will not anticipate the change on the economic system. In fact, if predictions based on historical data would be invalid when a policy change affects the economy, the economic agents are forward rather than backward-looking and adapt their expectations and behavior to the new policy stance. Thus, given some targets for the variables under study it is important to know the simultaneous future path that will lead to achieving those targets. Here it is considered the case in which a system of variables are to be forecasted with the aid of a VAR model with a cointegration relationship. The paths projected forward into the future as a combination of the model-based forecasts and the additional information provides what is known as a restricted forecast. This work is an attempt to contribute to the literature on Restricted Forecasting Theory for Multiple Time Series within the VAR framework. Specifically, Chapter 2 decomposes the JCT into single tests by a variance-covariance matrix associated with the restrictions and derives the formulas of a feasible JCT that accounts for estimated parameters. Chapter 3 develops, by Lagrangian optimization, the restricted forecasts of the multiple time series process with structural change, as well as its mean squared error. In addition, the univariate time series types of changes are considered here in a multivariate setting. Finally, Chapter 4 derives a methodology for forecasting multivariate time series that satisfy a contemporaneous binding constraint for which there exists a future target. A Monte Carlo study of a VEC model with one unit root shows that, for a forecast horizon large enough, the forecasts obtained with the proposed methodology are more efficient. A more detailed account of these contributions is provided below.

Author: LÓPEZ GARCÍA PEDRO.
Year: 2006.
University: COMPLUTENSE DE MADRID [More theses of this university] [www.ucm.es].
Place of defense: FACULTAD DE CC. POLÍTICAS Y SOCIOLOGÍA.

Summary: TELETRABAJO A DIFFERENT VISION tries to analyze a situation of labor where traditional concepts such as space and time are modified, in supporting new technologies. It has been necessary to conduct a descriptive tour of the information society, where it is located, and in the telecommunications sector, natural sphere of teleworkers under review, particularly in the company Vodafone. Why a different view? Because a first researches teleworkers and the socio-economic context that surrounds them, causing this situation corporate reorganizations. Concepts such as outsourcing of activities and policies of decentralization productive form parate of a strategy to make jobs disappear and appear visible in other businesses or outsourced services. Two links have been accompanying the whole, on the one hand labor relations, and on the other, trade unionism as descriptive prism. The unions, once had capacity to participate through social dialogue, have evolved in the valuation of telework, motivated largely by the incorporation in the international trade unionism. And finally, within the research team, has managed a practical guide to teleworking applicable in companies as a means to a better understanding of the phenomenon and possible regulation, negotiated, involving guarantees on the rights of teleworkers and lso measures for effective implementation of telework in the business world.