Search

This paper investigates the impact of energy efficiency along the unconditional distribution of residential property prices in Portugal. Using a dataset of more than 256,000 residential property sales from 2009 to 2013, a period that covers an economic depression, unconditional quantile regression analysis reveals that the responsiveness to energy efficiency improvements is different not only as we move from low- to high-priced residential units but also for apartments and houses. While the former show a downward trend in the magnitude of energy efficiency coefficient estimates, the opposite occurs for houses. The latter market segment exhibits clear market discounts at the lowest quantiles of the price distribution, something that is not observable thought conditional mean and quantile regression analysis. Results suggest the existence of a different responsiveness to energy efficiency improvements in the Lisbon region when compared to the rest of the country and that the impact of the Energy Performance Certificate label increases throughout time across all price quantiles. As a by-product of this paper, an unconditional quantile price index shows that the impact of the crisis was not the same across the different market segments, with price decreases being more severe for low- than high-priced properties. info:eu-repo/semantics/publishedVersion

Using a unique dataset containing information of around 256 thousand residential property sales, this paper discloses a clear sales premium for most energy efficient dwellings, which is more pronounced for apartments (13%) than for houses (5 to 6%). Cross-country comparisons support the finding that energy efficiency price premiums are higher in the Portuguese residential market than in central and northern European markets. Results emphasize the relevance of data issues in hedonic regression models. They illustrate how the use of appraisal prices, explanatory variables with measurement errors, and the omission of variables associated with the quality of the properties, may seriously bias energy efficiency partial effect estimates. These findings provide valuable information not only to policy-makers, but also to researchers interested in this area. info:eu-repo/semantics/publishedVersion

This paper provides an integrated approach for estimating parametric models from endogenous stratified samples. We discuss several alternative ways of removing the bias of the moment indicators usually employed under random sampling for estimating the parameters of the structural model and the proportion of the strata in the population. Those alternatives give rise to a bunch of moment-based estimators which are appropriate for both cases where the marginal strata probabilities are known and unknown. The derivation of our estimators is very simple and intuitive and incorporates as particular cases most of the likelihood-based estimators existing in the literature.

Empirical likelihood (EL) is appropriate to estimate moment condition models when a random sample from the target population is available. However, many economic surveys are subject to some form of stratification, in which case direct application of EL will produce inconsistent estimators. In this paper we propose a two-step EL (TSEL) estimator to deal with stratified samples in models defined by unconditional moment restrictions in presence of some aggregate information, which may consist, for example, of the mean and the variance of the variable of interest and/or the explanatory variables. A Monte Carlo simulation study reveals promising results for many versions of the TSEL estimator.

In this paper we propose a general framework to deal with datasets where a binary outcome is subject to misclassification and, for some sampling units, neither the error-prone variable of interest nor the covariates are recorded. A model to describe the observed data is for-malized and eficient likelihood-based generalized method of moments (GMM) estimators are suggested. These estimators merely require the formulation of the conditional distribution of the latent outcome given the covariates. The conditional probabilities which describe the error and the nonresponse mechanisms are estimated simultaneously with the parameters of inter-est. In a small Monte Carlo simulation study our GMM estimators revealed a very promising performance.

In this paper we propose a general framework to deal with the presence of covariate mea-surement error in endogenous stratifield samples. Using Chesher’s (2000) methodology, we develop approximately consistent estimators for the parameters of the structural model, in the sense that their inconsistency is of smaller order than that of the conventional estimators which ignore the existence of covariate measurement error. The approximate bias corrected estimators are obtained by applying the generalized method of moments (GMM) to a modifeld version of the moment indicators suggested by Imbens and Lancaster (1996) for endogenous stratified samples. Only the specification of the conditional distribution of the response vari-able given the latent covariates and the classical additive measurement error model assumption are required, the availability of information on both the marginal probability of the strata in the population and the variance of the measurement error not being essential. A score test to detect the presence of covariate measurement error arises as a by-product of this approach. Monte Carlo evidence is presented which suggests that, in endogenous stratified samples of moderate sizes, the modified GMM estimators perform well.

Mestrado Bolonha em Management As the conflict in politics becomes increasingly polarized, researchers in political science and psychology have become increasingly interested in determining the antecedents of individuals' attachment to ideologies. While some recent developments illustrate the relationship between political orientation and socio-demographic factors, personality traits, locus of control or risk aversion, this dissertation provides new insights for a possible relationship to financial literacy. A unidimensional model provides a simple understanding of the structure of political ideology; however, it has been shown to be implausible and insufficient. In this research, we highlight a model based on two dimensions: one for the economic freedom, and another for personal freedom. We construct a framework with data retrieved from a questionnaire connecting individual’s political orientation in the two-dimensional spectrum and its determinants with the use of ordered probit models. The results suggest an interplay between financial literacy and political orientation in the Left-Right dimension, in which being financially-literate increases the probability of an individual having Centre or Right-wing political views, in detriment of Left-wing views. We found no significance when considering the Libertarian-Authoritarian dimension. Furthermore, we analyse the effect of the highest level of education as an alternative measure of financial literacy and the results suggest that they capture different features and should, therefore, be interpreted as distinct variables. Several other variables included in the model were only proved significant in one of the dimensions. Our conclusions suggest that variables with economic links affect the dimension that refers to economic freedom such as financial literacy and average monthly income and, on the other hand, other variables such as region, age, ethnicity, or religion provide a better explanation of political orientation on a personal freedom dimension. info:eu-repo/semantics/publishedVersion

Mestrado Bolonha em Econometria Aplicada e Previsão This internship provides an insight on the creation attempt of a new rent index for commercial properties in Portugal, using monthly data, from an existing and functioning administrative mechanism - E-fatura, over the period 2016-2021. The mechanism E-fatura contains information about the Portuguese companies and individuals’ monthly billing. The purpose is to analyse if this information could be enough to translate into a new rent index or a proxy indicator without having to recur to lengthy classic methods,such as adjusting inquiries, or having to do a new type of specific census. In other words, the purpose is to try to extend the utility of an established receipt management mechanism in order to find if it could provide a detailed portrait of the commercial properties’ rent universe by itself. The information selected from E-fatura, although restricted to companies with economic activity related to the rental of real estate, is not exclusive to the renting universe of commercial properties and in that sense, it had to be limited and adapted to be in this line of work. Hedonic models were used for the index compilation and the method chosen was the time-dummy approach, first, by the adjacent time-dummy approach and second, by the (all-periods) pooled time-dummy method. After testing the different methods along with theoretical basis, a comparison between them is done, followed by an evaluation about the future viability of the index or proxy indicator. It was concluded that by using this approach, with all limitations considered, the computed index could capture macroeconomic dynamics and represent an overall correct picture of the market. Este relatório de estágio descreve a tentativa de criação de um novo índice de rendas para propriedades comerciais em Portugal, com dados mensais, através de um mecanismo administrativo, E-fatura, durante o período de 2016 a 2021. O mecanismo E-fatura contém informação sobre a faturação mensal de empresas e pessoas singulares portuguesas. O objetivo é analisar se a informação proveniente do mecanismo seria suficiente para calcular um novo índice de rendas sem ter de recorrer a métodos clássicos mais demorados tais como censos ou um novo questionário específico para esta situação. Em outras palavras, o objetivo é tentar alargar a utilidade de um mecanismo já estabelecido de gestão de faturas de forma a analisar se o universo de propriedades comerciais poderia ser retratado por este. A informação derivada do Efatura apesar de ter sido restrita apenas a empresas com atividade económica relacionada com o arrendamento de imobiliário, não é exclusiva a este universo e, como tal, necessitou ser limitada e ajustada para enquadrar o propósito deste relatório. Para a agregação do índice foram utilizados modelos hedónicos pela abordagem time-dummy: primeiramente pela time-dummy adjacente e consequentemente pela time-dummy englobando todos os períodos (pooled time-dummy). Após testar diferentes métodos, tendo por base a teoria apresentada, estes métodos foram comparados e avaliados quanto à sua futura viabilidade como índice. Com a abordagem de time-dummy adjacente, foi concluído que o índice final calculado tinha a capacidade de capturar dinâmicas macroeconómicas e representar o mercado de propriedades comerciais de uma forma geral. info:eu-repo/semantics/publishedVersion