This thesis is comprised of five papers that all relate to bootstrap methodology in analysis of non-stationary time series. The first paper starts with the fact that the Dickey-Fuller unit root test using asymptotic critical value has bad small sample performance. The small sample correction proposed by Johansen (2004) and bootstrap are two effective methods to improve the performance of the test. In this paper we compare these two methods as well as analyse the effect of bias-adjusting through a simulation study. We consider AR(1) and AR(2) models and both size and power properties are investigated. The second paper studies the asymptotic refinement of the bootstrap cointegration rank test. We expand the test statistic of a simplified VECM model and a Monte Carlo simulation was carried out to verify that the bootstrap test gives asymptotic refinement. The third paper focuses on the number of bootstrap replicates in bootstrap Dickey-Fuller unit root test. Through a simulation study, we find that a small number of bootstrap replicates are sufficient for a precise size, but, with too small number of replicates, we will lose power when the null hypothesis is not true. The fourth and last paper of the thesis concerns unit root test in panel setting focusing on the test proposed by Palm, Smeekes and Urbain (2011). In the fourth paper, we study the robustness of the PSU test with comparison with two representative tests from the second generation panel unit root tests. In the last paper, we generalise the PSU test to the model with deterministic terms. Two different methods are proposed to deal with the deterministic terms, and the asymptotic validity of the bootstrap procedure is theoretically checked. The small sample properties are studied by simulations and the paper is concluded by an empirical example. / <p>Ogiltigt ISBN: 978-91-554-9069-0</p>

nÃo hà / Unit root tests have been widely used to validate or reject economic modelâs hypotheses. Because of this, many authors have created different versions of this kind of test in order to generate statistics which are more precise in identifying the presence of a unit root. Some authors have increased the power of these statistics using panel data. However, the use of panel data brings the possibility of dependence between cross-sections, this has been initially handled by the independence between cross-sections hypothesis. Only the second generation tests consider dependence between cross-sections. Nevertheless, in the literature there is no test which allows changes in the dependence between cross-sections over time. Thus, this paper uses Monte Carlo experiments to analyze the small sample properties of some statistics used to identify the presence of a unit root. It is noticed that the size of these statistics has a large distortion when the level of dependence between cross-sections changes. / Teste de raiz unitÃria tem sido muito importante no sentido de validar ou rejeitar as hipÃteses dos modelos econÃmicos. Devido essa importÃncia, diversos autores tÃm criado diferentes versÃes desse teste, a fim de gerar estatÃsticas que sejam mais precisas em identificar a presenÃa de raiz unitÃria. Usando dados em painel, alguns autores conseguiram aumentar o poder dessas estatÃsticas. No entanto, o uso de dados em painel trÃs a possibilidade de dependÃncia cross-section nos dados, fato esse inicialmente tratado pela hipÃtese de independÃncia cross-section. Somente nos testes chamados de segunda geraÃÃo à que se trata dependÃncia cross-section. Entretanto, nÃo hà na literatura nenhum teste que permita mudanÃas nesse nÃvel de dependÃncia ao longo do tempo. Com isso, esse trabalho pretende avaliar, por meio de um experimento de Monte Carlo, as propriedades de pequenas amostras de algumas estatÃsticas usadas para identificar a presenÃa de raiz unitÃria. Percebe-se que o tamanho dessas estatÃsticas sofre uma grande distorÃÃo para as situaÃÃes de mudanÃa no nÃvel de dependÃncia cross-section.

Past focus in the panel gravity literature has been on multidimensional fixed effects specifications in an effort to accommodate heterogeneity. After introducing conventional multidimensional fixed effects, we find evidence of cross-sectional dependence in flows. We propose a simultaneous dependence gravity model that allows for network dependence in flows, along with computationally efficient Markov Chain Monte Carlo estimation methods that produce a Monte Carlo integration estimate of log-marginal likelihood useful for model comparison. Application of the model to a panel of trade flows points to network spillover effects, suggesting the presence of network dependence and biased estimates from conventional trade flow specifications. The most important sources of network dependence were found to be membership in trade organizations, historical colonial ties, common currency and spatial proximity of countries. / Series: Working Papers in Regional Science

Past focus in the panel gravity literature has been on multidimensional fixed effects specifications in an effort to accommodate heterogeneity. After introducing fixed effects for each origin- destination dyad and time-period speciffic effects, we find evidence of cross-sectional dependence in flows. We propose a simultaneous dependence gravity model that allows for network dependence in flows, along with computationally efficient MCMC estimation methods that produce a Monte Carlo integration estimate of log-marginal likelihood useful for model comparison. Application of the model to a panel of trade flows points to network spillover effects, suggesting the presence of network dependence and biased estimates from conventional trade flow specifications. / Series: Working Papers in Regional Science

Cette thèse comporte quatre essais et porte sur les questions fondamentales sur la relation entre l’environnement et le développement économique. Le premier chapitre cherche à identifier les déterminants individuels et contextuels qui affectent la volonté de contribuer des gens à la lutte contre la pollution environnementale. Nos résultats révèlent que les individus riches, les personnes éduquées ainsi que les personnes possédant des valeurs post-matérialistes sont plus susceptibles d’être préoccupées par la pollution environnementale. On remarque que la caractéristique du pays de ces individus affecte leur volonté à contribuer. Ainsi, dans les pays à forte démocratie avec une forte stabilité gouvernementale, les individus sont réticents à faire des dons pour prévenir les dommages environnementaux. Le deuxième chapitre examine la relation entre la croissance économique et la dégradation de l’environnement en s’interrogeant sur la relation U inversée de Kuznets. Nos résultats empiriques ne révèlent aucune preuve de ladite relation. Cependant, nous notons l’existence d’une relation non linéaire entre la croissance économique et la dégradation de l’environnement. Les émissions ont tendance à augmenter un rythme plus rapide dans les premiers stades de la croissance économique puis dans les dernière étapes, cette hausse persiste mais à un rythme plus lent. Le troisième chapitre étudie la relation de causalité de long terme entre la consommation d'énergie propre et la croissance économique dans un groupe de pays de l’Afrique subsaharienne. Le résultat révèle l'existence d'une relation d'équilibre à long terme entre la consommation d'énergie propre et la croissance économique. En outre, la dynamique de court terme et de long terme indiquent une relation de causalité à la Granger unidirectionnelle de la consommation d'énergie propre vers la croissance économique sans aucun effet rétroactif. Le dernier chapitre de cette thèse cherche à investiguer sur la convergence des émissions de gaz entre les provinces canadiennes. L'étude montre que les émissions de gaz des provinces canadiennes sont caractérisées des convergences de clubs. En d'autres termes, on détecte l'existence d'une segmentation des émissions entre les provinces canadiennes. / This thesis comprises four empirical essays on environmental and development economics. In the first chapter, we examine to what extent individual and contextual level factors influence individuals to contribute financially to prevent environmental pollution. We find that rich people, individuals with higher education, as well as those who possess post-materialist values are more likely to be concerned about environmental pollution. We also observe the country in which individuals live matter in their willingness to contribute. More precisely, we find democracy and government stability reduce individuals’ intention to donate to prevent environmental damage mainly in developed countries. The second chapter deals with the relation between economic growth and environmental degradation by focusing on the issue of whether the inverted U-shaped relation exist. The study discloses no evidence for the U-shaped relation. However, the empirical result points toward a non-linear relationship between environmental degradation and economic growth, that is, emissions tend to rise rapidly in the early stages with economic growth, and then emissions continue to increase but a lower rate in the later stages. The third chapter investigates the long-run as well as the causal relationship between energy consumption and economic growth in a group of Sub-Saharan Africa. The result discovers the existence of a long-run equilibrium relationship between clean energy consumption and economic growth. Furthermore, the short-run and the long-run dynamics indicate unidirectional Granger causality running from clean energy consumption to economic growth without any feedback effects. The last chapter of this thesis concerns with convergence of emissions across Canadian provinces. The study determines convergence clubs better characterizes Canadian’s emissions. In other words, we detect the existence of segmentation in emissions across Canadian provinces.

The aim of the master thesis is to empirically analyze if there is a support for new classics or new Keynesians as a dominant theory of short-run aggregate supply curve. The analysis is based on dynamic panel data model for 38 countries and period between 1970 and 2014. Because the results show some evidence on negative significance of level of inflation in contrast with its variability, I conclude that there is support for the new Keynesian theory. I focus on examination of the panel data assumptions such as the stationarity of explanatory variables, existence of the individual or random effects, validity of homogeneity of slope coefficients and mainly the cross-sectional dependence of error terms. After testing for these assumptions, I choose the most suitable method of estimation for dynamic panel data models. I use these methods for analyzing both linear and non-linear specification of the given model. As a result, we can see that the selection of right estimation method plays a great role in final outcomes. I also check model robustness by including changes of real oil price as a proxy variable for the supply shock in the economy.