Dieter Wang

PhD Candidate
Consultant for the World Bank
PhD Candidate in Financial Econometrics and Climate Finance
Consultant for the World Bank
PhD Candidate in Financial Econometrics and Climate Finance
Tinbergen Institute and Vrije Universiteit Amsterdam
Research
Climate finance Environmental risks have entered the financial world. Investors, insurances and regulartors are aware of this risk source that affects both developed and developing countries. However, putting a number of this risk remains a challenge. To understand its impact on sovereign bonds and their yield curves, I combine machine learning methods with traditional dynamic factor models and relate them to environmental variables and climate risks.
Financial contagion Does credit risk spread between banks because of their similar businesses models? Or do structural determinants drive common dynamics? Standard credit models treat banks as isolated entities. We allow a bank's creditworthiness to be a function of other banks, that are similar enough to be informative. As a visiting researcher at the Dutch Central Bank, I find answers to this question with detailed supervisory datasets on the largest banks in the Eurozone.
Network econometrics Network effects in banking systems or in asset pricing are unobserved and can have nonlinear effects — idiosyncratic shocks can become systematic through the amplifying role of networks. Furthermore, financial network effects are inherently dynamic. The estimation of such effects is further complicated by stochastic volatilty. As a solution, I treat network effects as latent state variables and use particle filters for likelihood estimation.
World Bank
Greening the financial sector As a consultant for the Environment and Natural Resources unit, I tried to identify what role environmental variables play in sovereign risk. See here for a report on our project. In a more recent appointment at the Finance, Competitiveness and Innovation, Long-Term Finance unit, I assess how these risks impact the financial sector with focus on physical risks and conduct empirical research on environmental risks and opportunities.
Famine prediction As a modeling consultant for the Fragility, Conflict and Violence unit, I collaborate with leading insurance companies and global tech companies on the Famine Action Mechanism. In this project, I developed a stochastic model to understand and predict the population dynamics in food insecurity. See here (World Bank) and here (Washington Post) for press coverage of our project.
Education
since 2016 Tinbergen Institute and VU Amsterdam, NL
PhD in Financial Econometrics (expected graduation in 2020)
Columbia University in the City of New York, US
Visiting Scholar, Columbia Buiness School
Host: Paul Glasserman
2014-2016 Tinbergen Institute and University of Amsterdam, NL
MPhil in Economics (Econometrics and Finance tracks)
2010-2014 Eberhard-Karls-University Tübingen, DE
B.Sc. International Economics
The University of Hong Kong, HK
Exchange Year, BEcon&Fin
Publications
Working papers
Stochastic Modeling of Food Insecurity
with Bo Pieter Johannes Andrée, Andres Chamorro and Phoebe Girouard Spencer (2020)
World Bank Policy Research Working Papers No. 9413
show abstract
Recent advances in food insecurity classification have made analytical approaches to predict and inform response to food crises possible. This paper develops a predictive, statistical framework to identify drivers of food insecurity risk with simulation capabilities for scenario analyses, risk assessment and forecasting purposes. It utilizes a panel vector-autoregression to model food insecurity distributions of 15 Sub-Saharan African countries between October 2009 and February 2019. Statistical variable selection methods are employed to identify the most important agronomic, weather, conflict and economic variables. The paper finds that food insecurity dynamics are asymmetric and past-dependent, with low insecurity states more likely to transition to high insecurity states than vice versa. Conflict variables are more relevant for dynamics in highly critical stages, while agronomic and weather variables are more important for less critical states. Food prices are predictive for all cases. A Bayesian extension is introduced to incorporate expert opinions through the use of priors, which lead to significant improvements in model performance.
Predicting Food Crises
with Bo Pieter Johannes Andrée, Aart C. Kraay, Andres Chamorro and Phoebe Girouard Spencer (2020)
World Bank Policy Research Working Papers No. 9412
show abstract
Globally, more than 130 million people are estimated to be in food crisis. These humanitarian disasters are associated with severe impacts on livelihoods that can reverse years of development gains. The existing outlooks of crisis-affected populations rely on expert assessment of evidence and are limited in their temporal frequency and ability to look beyond several months. This paper presents a statistical foresting approach to predict the outbreak of food crises with sufficient lead time for preventive action. Different use cases are explored related to possible alternative targeting policies and the levels at which finance is typically unlocked. The results indicate that, particularly at longer forecasting horizons, the statistical predictions compare favorably to expert-based outlooks. The paper concludes that statistical models demonstrate good ability to detect future outbreaks of food crises and that using statistical forecasting approaches may help increase lead time for action.
Smooth marginalized particle filters for dynamic network effect models
with Julia Schaumburg (2020)
Tinbergen Institute Discussion Paper 2020-023/III
show abstract
We propose a dynamic network model for the study of high-dimensional panel data. Crosssectional dependencies between units are captured via one or multiple observed networks and a low-dimensional vector of latent stochastic network intensity parameters. The parameterdriven, nonlinear structure of the model requires simulation-based filtering and estimation, for which we suggest to use the smooth marginalized particle filter (SMPF). In a Monte Carlo simulation study, we demonstrate the SMPF’s good performance relative to benchmarks, particularly when the cross-section dimension is large and the network is dense. An empirical application on the propagation of COVID-19 through international travel networks illustrates the usefulness of our method.
Do information contagion and business model similarities explain bank credit risk commonalities?
with Julia Schaumburg, Iman van Lelyveld (2019)
ESRB Working Paper Series, No 94.
show abstract
This paper revisits the credit spread puzzle for banks from the perspective of information contagion. The puzzle consists of two stylized facts: Structural determinants of credit risk not onlyhave low explanatory power but also fail to capture common factors in the residuals. We reproduce the puzzle for European bank credit spreads and hypothesize that the puzzle exists because structural models ignore contagion effects. We therefore extend the structural approach to include information contagion through bank business model similarities. To capture this channel, we propose an intuitive measure for portfolio overlap and apply it to the complete asset holdings of the largest banks in the Eurozone. Incorporating this unique network information into the structural model increases explanatory power and removes a systemic common factor fromthe residuals. Furthermore, neglecting the network likely overstates the importance of structural determinants.
Pollution and Expenditures in a Penalized Vector Spatial Autoregressive Time Series Model with Data-Driven Networks
with Bo Pieter Johannes Andrée, Phoebe Girouard Spencer, Sardar Azari, Andres Chamorro and Harun Dogo (2019)
World Bank Policy Research Working Papers No. 8757
show abstract
This paper introduces a Spatial Vector Autoregressive Moving Average (SVARMA) model in which multiple cross-sectional time series are modeled as multivariate, possibly fat-tailed, spatial autoregressive ARMA processes. The estimation requires specifying the cross-sectional spillover channels through spatial weights matrices. the paper explores a kernel method to estimate the network topology based on similarities in the data. It discusses the model and estimation, focusing on a penalized Maximum Likelihood criterion. The empirical performance of the estimator is explored in a simulation study. The model is used to study a spatial time series of pollution and household expenditure data in Indonesia. The analysis finds that the new model improves in terms of implied density, and better neutralizes residual correlations than the VARMA, using fewer parameters. The results suggest that growth in household expenditures precedes pollution reduction, particularly after the expenditures of poorer households increase; that increasing pollution is followed by reduced growth in expenditures, particularly reducing the growth of poorer households; and that there are significant spillovers from bottom-up growth in expenditures. The paper does not find evidence for top-down growth spillovers. Feedback between the identified mechanisms may contribute to pollution-poverty traps and the results imply that pollution damages are economically significant.
Work in progress
Natural capital and the term-structure of sovereign bonds
with myself
Asset pricing through peer networks
with Julia Schaumburg
Seminars and Conferences
2020
[scheduled] 14th International Conference on Computational and Financial Econometrics, King's College London
Asset-level Data Annual Meeting, Sustainable Finance Institute, Oxford University
2019
Paris December 2019 Finance Meeting [*]
European Commission, Joint Research Centre, Summer School Sustainable Finance (presentation)
2018
71st European Meeting of the Econometric Society (EEA-ESEM), Cologne
International Banking, Economics and Finance Association 2018 Summer Meeting, Vancouver
Research Seminar, International Monetary Fund (MCM), Washington D.C.
Research Lunch Seminar, Federal Reserve Board, Washington D.C.
Research Seminar, Office of Financial Research, Washington D.C.
2018 RiskLab/BoF/ESRB Conference on Systemic Risk Analytics, Bank of Finland
DNB Research Lunch Seminar, De Nederlandsche Bank
2017
Workshop on spatial and spatio-temporal data analysis, Tohoku University - invited guest speaker
International Finance and Banking Society Conference, Saïd Business School, Oxford University
Tinbergen Institute PhD Finance Seminar, Tinbergen Institute Amsterdam
2016
VU Econometrics Brown Bag Seminar, VU Amsterdam
Teaching
Graduate level
Lecturer/TA, Machine Learning for Finance, VU Amsterdam
Lecturer, Financial Econometrics in Python, Northeast Normal University
TA/Lecturer, Financial Markets and Institutions, VU Amsterdam
TA, Empirical Finance and Accounting (Stata), VU Amsterdam
TA, Advanced Asset Management, Amsterdam Business School
TA, Mathematics I, Tinbergen Institute
TA, Introduction to Programming + LaTeX course (Matlab, Ox), Tinbergen Institute
Undergraduate level
Supervisor, Bachelor Thesis, VU Amsterdam
TA, Finance I, VU Amsterdam
TA, Quantitative Methods of Economics, Eberhard Karls Universität Tübingen
TA, Intermediate Microeconomics, Eberhard Karls Universität Tübingen
TA, Risk and Probability, Eberhard Karls Universität Tübingen
TA, Mathematical Methods of Economics, Eberhard Karls Universität Tübingen
VU Online Summer Prep-Campus
I'm the project manager for the Mathematics Prep-Campus for which we won the VU Innovation Prize 2017.
https://vu.prep-campus.nl
Honors and Awards
2015, DAAD Graduate Scholarship
2014, Tinbergen Institute Scholarship
2012, DAAD Full-Year Exchange Scholarship
Refereeing
International Finance
Regional Science and Urban Economics
Visualizations
Contact
Vrije Universiteit Amsterdam
Department of Finance
7A-47 De Boelelaan 1105
1081HV Amsterdam.
d.wangatvu.nl

Visit my page