Search

This paper provides statistical learning techniques for determining the full own-price market impact and the relevance and effect of cross-price and cross-asset spillover channels from intraday transactions data. The novel tools allow extracting comprehensive information contained in the limit order books (LOB) and quantify their impacts on the size and structure of price interdependencies across stocks. For correct empirical network determination of such dynamic liquidity price effects even in small portfolios, we require high-dimensional statistical learning methods with an integrated general bootstrap procedure. We document the importance of LOB liquidity network spillovers even for a small blue-chip NASDAQ portfolio.

An accurate assessment of tail inequalities and tail asymmetries of financial returns is key for risk management and portfolio allocation. We propose a new test procedure for detecting the full extent of such structural differences in the dependence of bivariate extreme returns. We decompose the testing problem into piecewise multiple comparisons of Cramér-von Mises distances of tail copulas. In this way, tail regions that cause differences in extreme dependence can be located and consequently be targeted by financial strategies. We derive the asymptotic properties of the test and provide a bootstrap approximation for finite samples. Moreover, we account for the multiplicity of the piecewise tail copula comparisons by adjusting individual p-values according to multiple testing techniques. Monte Carlo simulations demonstrate the test's superior finite-sample properties for common financial tail risk models, both in the i.i.d. and the sequentially dependent case. During the last 90 years in US stock markets, our test detects up to 20% more tail asymmetries than competing tests. This can be attributed to the presence of non-standard tail dependence structures. We also find evidence for diminishing tail asymmetries during every major financial crisis - except for the 2007-09 crisis - reflecting a risk-return trade-off for extreme returns.

We consider the problem of testing for an omitted multiplicative long-term component in GARCH-type models. Under the alternative there is a two-component model with a short-term GARCH component that uctuates around a smoothly time-varying long-term component which is driven by the dynamics of an explanatory variable. We suggest a Lagrange Multiplier statistic for testing the null hypothesis that the variable has no explanatory power. We derive the asymptotic theory for our test statistic and investigate its finite sample properties by Monte-Carlo simulation. Our test also covers the mixed-frequency case in which the returns are observed at a higher frequency than the explanatory variable. The usefulness of our procedure is illustrated by empirical applications to S&P 500 return data.

We study the impact of changes in regulations and policy interventions on systemic risk among European sovereigns measured as volatility spillovers in respective credit risk markets. Our unique intraday CDS dataset allows for precise measurement of the effectiveness of these events in a network setting. In particular, it allows discerning interventions which entail significant changes in network cross-effects with appropriate bootstrap confidence intervals. We show that it was mainly regulatory changes with the ban of trading naked sovereign CDS in 2012 as well as the new ISDA regulations in 2014 which were most effective in reducing systemic risk. In comparison, we find that the effect of policy interventions was minor and generally not sustainable. In particular, they only had a significant impact when implemented for the first time and when targeting more than one country. For the volatility spillover channels, we generally find balanced networks with no fragmentation over time.

This paper analyzes the market impact of limit order books (LOB) taking crossstock effects into account. Based on penalized vector autoregressive approach, we aim to identify significance and magnitude of the directed network channels within and between LOBs by bootstrapped impulse response functions. Moreover, information on asymmetries and imbalances within the LOB over time would be derived. For the sample of a NASDAQ blue-chip portfolio during 06-07/2016 we find that LOB network effects crucially determine prices and bid-ask asymmetries are prevalent.

In practice, multivariate dependencies between extreme risks are often only assessed in a pairwise way. We propose a test for detecting situations when such pairwise measures are inadequate and give incomplete results. This occurs when a significant portion of the multivariate dependence structure in the tails is of higher dimension than two. Our test statistic is based on a decomposition of the stable tail dependence function describing multivariate tail dependence. The asymptotic properties of the test are provided and a bootstrap based finite sample version of the test is proposed. A simulation study documents good size and power properties of the test including settings with time-series components and factor models. In an application to stock indices for non-crisis times, pairwise tail models seem appropriate for global markets while the test finds them not admissible for the tightly interconnected European market. From 2007/08 on, however, higher order dependencies generally increase and require a multivariate tail model in all cases.

We introduce a methodology for measuring default risk connectedness that is based on an out-of-sample variance decomposition of model forecast errors. The out-of-sample nature of the procedure leads to "realized" measures which, in practice, respond more quickly to crisis occurrences than those based on in-sample methods. The resulting relative and absolute connectedness measures find distinct and complementary information from CDS and bond yield data on European area sovereign risk. The detection and use of these second moment differences of CDS and bond data is new to the literature and allows to identify countries that impose risk on the system from those which sustain risk.

We develop a misspecification test for the multiplicative two-component GARCH-MIDAS model suggested in Engle et al. (2013). In the GARCH-MIDAS model a short-term unit variance GARCH component fluctuates around a smoothly time-varying long-term component which is driven by the dynamics of an explanatory variable. We suggest a Lagrange Multiplier statistic for testing the null hypothesis that the variable has no explanatory power. Hence, under the null hypothesis the long-term component is constant and the GARCH-MIDAS reduces to the simple GARCH model. We derive the asymptotic theory for our test statistic and investigate its finite sample properties by Monte-Carlo simulation. The usefulness of our procedure is illustrated by an empirical application to S&P 500 return data.

In an increasingly digital world, data has become abundant and research about leveraging such vast amounts of data is on the rise. While extracting important information relevant for economic policies or financial risk is crucial, the often non-standard structure of such observational data poses many challenges for researchers. That includes highly correlated, time-dependent data, combinations of unstructured data, and even high-dimensional situations, where we have very few data points and many potentially relevant factors. In this thesis, I tackle the above challenges by developing interpretable statistical machine learning methods to reveal important effects of public policies, to better assess risks in financial applications, and to quantify market drivers. I study causal inference, statistical model selection, and prediction in different social and economic contexts in order to uncover statistical relationships and to identify important contributing factors. In the first part of my work, I analyze financial risk with cryptocurrencies and corporate bonds. For the former, I identify classes of assets and time periods where flexible machine learning methods, such as random forests employed within a statistical framework, significantly improve predictability of risk. This is vital given the highly volatile return structure of cryptocurrencies. For corporate bonds, I uncover drivers of the risk of default by developing a method that correctly handles the underlying, highly correlated, time series data. In the second part, I focus on the evaluation of the causal effect of tuition fees on university student enrollment. I develop methods to deal with the many possible influencing factors given only few observations by combining subsampling-based methods with regularization in a panel setup. I can show that there was a causal effect of the short tuition fee period in Germany by disentangling this effect from other factors and policies. In the third part, I combine satellite images with many noisy, observational data sources to show the impact of crime on the housing market of New York City on a spatial grid. To overcome the endogeneity of crime for house prices, I develop a method that leverages satellite data, can be easily extended to other cities, and highlights the non-linearity of crime on a spatial level.

Das moderne Finanzsystem ist komplex, dynamisch, hochdimensional und oftmals nicht stationär. All diese Faktoren stellen große Herausforderungen beim Messen des zugrundeliegenden Finanzrisikos dar, das speziell für Marktteilnehmer von oberster Priorität ist. Hochdimensionalität, die aus der ansteigenden Vielfalt an Finanzprodukten entsteht, ist ein wichtiges Thema für Ökonometriker. Ein Standardansatz, um mit hoher Dimensionalität umzugehen, ist es, Schlüsselvariablen auszuwählen und kleine Koeffizientenen auf null zu setzen, wie etwa Lasso. In der Finanzmarktanalyse kann eine solche geringe Annahme helfen, die führenden Risikofaktoren aus dem extrem großen Portfolio, das letztendlich das robuste Maß für finanzielles Risiko darstellt, hervorzuheben. In dieser Arbeit nutzen wir penalisierte Verfahren, um die ökonometrischen Maße für das finanzielle Risiko in hoher Dimension zu schätzen, sowohl mit nieder-, als auch hochfrequenten Daten. Mit Fokus auf dem Finanzmarkt, können wir das Risikonetzwerk des ganzen Systems konstruieren, das die Identifizierung individualspezifischen Risikos erlaubt. Modern financial system is complex, dynamic, high-dimensional and often possibly non-stationary. All these factors pose great challenges in measuring the underlying financial risk, which is of top priority especially for market participants. High-dimensionality, which arises from the increasing variety of the financial products, is an important issue among econometricians. A standard approach dealing with high dimensionality is to select key variables and set small coefficient to zero, such as lasso. In financial market analysis, such sparsity assumption can help highlight the leading risk factors from the extremely large portfolio, which constitutes the robust measure for financial risk in the end. In this paper we use penalized techniques to estimate the econometric measures of financial risk in high dimensional, with both low-frequency and high-frequency data. With focus on financial market, we could construct the risk network of the whole system which allows for identification of individual-specific risk.