<p> This dissertation carries out a series of Monte Carlo simulations seeking the implications for welfare estimates from three research practices commonly implemented in empirical applications of mixed logit and latent class logit. </p><p> Chapter 3 compares welfare measures across conditional logit, mixed logit, and latent class logit. The practice of comparing welfare estimates is widely used in the field. However, this chapter shows comparisons of welfare estimates seem unable to provide reliable information about the differences in welfare estimates that result from controlling for unobserved heterogeneity. The reason is that estimates from mixed logit and latent class logit are inherently inecient and inaccurate. </p><p> Researchers tend to use their own judgement to select the number of classes of a latent class logit. Chapter 4 studies the reliability of welfare estimates obtained under two scenarios for which an empirical researcher using his/her judgement would arguably choose less classes than the true number of classes. Results show that models with a number of classes smaller than the true number tend to yield down- ward biased and inaccurate estimates. The latent class logit with the true number of classes always yield unbiased estimates but their accuracy may be worse than models with the smaller number of classes. </p><p> Studies implementing discrete choice experiments commonly obtain estimates of preference parameters from latent class logit models. This practice, however, implies a mismatch: discrete choice experiments are designed under the assumption of homogeneity in preferences, and latent class logit search for heterogeneous preferences. Chapter 5 studies whether welfare estimates are robust to this mismatch. This chapter checks whether the number of choice tasks impact the reliability of welfare estimates. The findings show welfare estimates are unbiased regardless the number of choice tasks, and their accuracy increases with the number of choice tasks. However, some of the welfare estimates are inefficient to the point that cannot be statistically distinguished from zero, regardless the number of choice tasks. </p><p> Implications from these findings for the empirical literature are discussed. </p>

The Sustainable Development Goals (SDGs) express the commitment of countries to integrate ecosystem and biodiversity values into national planning. The System of Environmental-Economic Accounting – Experimental Ecosystem Accounting (SEEA-EEA) is an emerging international standard measurement framework for national ecosystem accounting. The international official statistics community proposes the SEEA-EEA as a means of integrating ecosystem and biodiversity values into national planning by providing guidance on measuring ecosystems and their contribution to the economy. Implementation of such a common measurement framework requires agreement among diverse ethical perspectives, disciplines, national contexts and roles on what to measure, how to measure it and how to interpret those measures to support a common policy direction. This thesis asks the question: If the aim is to provide guidance to countries on integrating ecosystem and biodiversity values into national planning, how could one foster convergence on a common national ecosystem accounting framework that is sufficiently comprehensive to capture the important linkages between ecosystems and human well-being, sufficiently convergent to be accepted by diverse perspectives, sufficiently rigorous for national official statistics, sufficiently consistent to allow for time-series and international comparisons and sufficiently feasible to be affordable for national governments to implement and maintain? To address this broader question, this thesis investigates the sources of divergence in national ecosystem accounting and develops tools to assess and to foster convergence. To accomplish this, I focussed on the following four research questions in four separate papers: 1. How should we think about ecosystem measurement if the aim is comprehensiveness, practicality, and convergence? [Chapter 2] This ethical analysis concludes that for ecosystem accounting to be universal, it needs to explicitly and simultaneously address broad human values, long time-frames, and the concepts of Critical Natural Capital and precaution. 2. What approaches to ecosystem accounting have already been developed and are they sufficient? [Chapter 3] This review of 16 state-of-the-art frameworks finds that none addresses all requirements for convergence on a common national ecosystem accounting framework. Collectively, they provide insufficient guidance on ecosystem classification, measurement in general, delineating Critical Natural Capital, incorporating broad human values and measuring statistical uncertainty. 3. Where is the divergence of values and preferences within the broader community of practice (researchers, users, analysts)? [Chapter 4] This cluster analysis of a survey of 131 expert stakeholders in national ecosystem accounting revealed agreement on the need for broadening the scope, addressing multiple decision contexts and furthering the development of national ecosystem accounting. The most important divergence issues in this community of practice were attributed to different ethical perspectives and differences in interpretation of core concepts. 4. Are current classifications of ecosystems and ecosystem services sufficient for national ecosystem accounting? [Chapter 5] This meta-analysis integrates nine comprehensive ecosystem assessments. It concludes that the lack of rigour in current classifications impedes consensus on aggregating information on “Which ecosystems produce which services?” and therefore current approaches are insufficient for national ecosystem accounting. I suggest an improved ecosystem classification for future studies. In the concluding chapter, I present a synthesis of research arguments and findings of the previous four chapters. The main outcome of this research has been not only the specific findings of the individual chapters, but also the development of a normative and empirically-supported toolkit to improve convergence and aggregation in future national ecosystem accounting frameworks: - Four normative criteria to assess frameworks and to incorporate into future designs and revisions, - A critical comparative assessment of current frameworks, - An empirically supported analysis of the preferences of the community of practice, and - A systematic approach for determining priority ecosystems and services for national ecosystem accounting. This thesis concludes that national ecosystem accounting can be a valuable tool for national planning. The approaches suggested can be applied to establishing a constructive national dialogue on national environmental priorities, to provide evidence to inform those priorities and to apply this evidence to support common policy platforms. However, care must be taken in its implementation to minimize the inherent risks of oversimplification and homogenization of the diverse stakeholder and scientific perspectives.

There has been an increasing demand for describing, predicting, and drawing inferences for various environmental processes, such as air pollution and precipitation. Environmental statistics plays an important role in many related applications, such as weather-related risk assessment for urban design and crop growth. However, modeling the spatio-temporal dynamics of environmental data is challenging due to their inherent high variability and nonstationarity. This dissertation is composed of four signi cant contributions to the modeling, simulation, and prediction of spatiotemporal processes using statistical techniques and machine learning algorithms. This dissertation rstly focuses on the Gaussian process emulators of the numerical climate models over a large spatial region, where the spatial process exhibits nonstationarity. The proposed method allows for estimating a rich class of nonstationary Mat ern covariance functions with spatially varying parameters. The e cient estimation is achieved by local-polynomial tting of the covariance parameters. To extend the applicability of this method to large-scale computations, the proposed method is implemented by developing software with high-performance computing architectures for nonstationary Gaussian process estimation and simulation. The developed software outperforms existing ones in both computational time and accuracy by a large margin. The method and software are applied to the statistical emulation of high-resolution climate models. The second focus of this dissertation is the development of spatio-temporal stochastic weather generators for non-Gaussian and nonstationary processes. The proposed multi-site generator uses a left-censored non-Gaussian vector autoregression model, where the random error follows a skew-symmetric distribution. It not only drives the occurrence and intensity simultaneously but also possesses nice interpretations both physically and statistically. The generator is applied to 30-second precipitation data collected at the University of Lausanne. Finally, this dissertation investigates the spatial prediction with scalable deep learning algorithms to overcome the limitations of the classical Kriging predictor in geostatistics. A novel neural network structure is proposed for spatial prediction by adding an embedding layer of spatial coordinates with basis functions. The proposed method, called DeepKriging, has multiple advantages over Kriging and classical neural networks with spatial coordinates as features. The method is applied to the prediction of ne particulate matter (PM2:5) concentrations in the United States.

Cette thèse présente des contributions à la littérature des méthodes de Monte Carlo utilisé dans l'analyse des modèles complexes en statistique Bayésienne; l'accent est mis à la fois sur la complexité des modèles et sur les difficultés de calcul.Le premier chapitre élargit Delayed Acceptance, une variante computationellement efficace du Metropolis--Hastings, et agrandit son cadre théorique fournissant une justification adéquate pour la méthode, des limits pour sa variance asymptotique par rapport au Metropolis--Hastings et des idées pour le réglage optimal de sa distribution instrumentale.Nous allons ensuite développer une méthode Bayésienne pour analyser les processus environnementaux non stationnaires, appelées Expansion Dimension, qui considère le processus observé comme une projection depuis une dimension supérieure, où l'hypothèse de stationnarité pourrait etre acceptée. Le dernier chapitre sera finalement consacrée à l'étude des structures de dépendances conditionnelles par une formulation entièrement Bayésienne du modèle de Copule Gaussien graphique. / This thesis presents contributions to the Monte Carlo literature aimed toward the analysis of complex models in Bayesian Statistics; the focus is on both complexity related to complicate models and computational difficulties.We will first expand Delayed Acceptance, a computationally efficient variant ofMetropolis--Hastings, to a multi-step procedure and enlarge its theoretical background, providing proper justification for the method, asymptotic variance bounds relative to its parent MH kernel and optimal tuning for the scale of its proposal.We will then develop a flexible Bayesian method to analyse nonlinear environmentalprocesses, called Dimension Expansion, that essentially consider the observed process as a projection from a higher dimension, where the assumption of stationarity could hold.The last chapter will finally be dedicated to the investigation of conditional (in)dependence structures via a fully Bayesian formulation of the Gaussian Copula graphical model.

Welche Strategien verfolgen die Bundesregierung und die Bundesländer der Bundesrepublik Deutschland, um den anthropogen bedingten Treibhauseffekt zu mindern und etwaige Folgen abzuwenden? Für die vorliegende Analyse ist diese Frage der Ausgangpunkt. Es wird ein Überblick über die jeweiligen Klimaschutzstrategien und den Grad der Zielerreichung gegeben. Ziel dieser Arbeit ist die Veröffentlichung der Ergebnisse im Internet auf der Domain www.klimastrategie.de. Den Klimaschutzanstrengungen zugrunde liegende Dokumente der Bundesländer und des Bundes werden, soweit veröffentlicht, vollständig im Internet dokumentiert.

Welche Strategien verfolgen die Bundesregierung und die Bundesländer der Bundesrepublik Deutschland, um den anthropogen bedingten Treibhauseffekt zu mindern und etwaige Folgen abzuwenden? Für die vorliegende Analyse ist diese Frage der Ausgangpunkt. Es wird ein Überblick über die jeweiligen Klimaschutzstrategien und den Grad der Zielerreichung gegeben. Ziel dieser Arbeit ist die Veröffentlichung der Ergebnisse im Internet auf der Domain www.klimastrategie.de. Den Klimaschutzanstrengungen zugrunde liegende Dokumente der Bundesländer und des Bundes werden, soweit veröffentlicht, vollständig im Internet dokumentiert.:1. Einleitung 2. Vorgehensweise 3. Zusammenfassung 4. Die Klimaschutzstrategie der deutschen Bundesregierung 5. Die Klimaschutzstrategien der deutschen Bundesländer 5.1. Umweltökonomische Gesamtrechung der Länder (UGR) 5.2. Die Klimaschutzstrategie im Land Baden-Württemberg 5.3. Die Klimaschutzstrategie im Freistaat Bayern 5.4. Die Klimaschutzstrategie im Land Berlin 5.5. Die Klimaschutzstrategie im Land Brandenburg 5.6. Die Klimaschutzstrategie im Land Bremen 5.7. Die Klimaschutzstrategie in der Freien und Hansestadt Hamburg 5.8. Die Klimaschutzstrategie im Land Hessen 5.9. Die Klimaschutzstrategie im Land Mecklenburg-Vorpommern 5.10. Die Klimaschutzstrategie im Land Niedersachsen 5.11. Die Klimaschutzstrategie im Land Nordrhein-Westfalen 5.12. Die Klimaschutzstrategie im Land Rheinland-Pfalz 5.13. Die Klimaschutzstrategie im Saarland 5.14. Die Klimaschutzstrategie im Freistaat Sachsen 5.15. Die Klimaschutzstrategie im Land Sachsen-Anhalt 5.16. Die Klimaschutzstrategie im Land Schleswig-Holstein 5.17. Die Klimaschutzstrategie im Freistaat Thüringen 5.18. Der Sektor Verkehr in den Klimaschutzstrategien 6. Fazit 7. Das Internetportal klimastrategie.de 8. Quellenverzeichnis