Research Seminars

Risk Related Brain Regions Detected with 3D Image FPCA

Speaker(s): 
Ying Chen (National University of Singapore)
Date: 
Monday, June 22, 2015 - 2:00pm
Location: 
Spandauer Straße 1, Room 23

Risk attitude and perception is reflected in brain reactions during an RPID experiment. Given the fMRI data, the question is how to detect the risk related regions and explain the relation between people's risk preference and brain activity. Conventional methods are often insensitive to the original spatial patterns and interdependence of the fMRI data.

Inference problems in high dimensional linear models

Speaker(s): 
Alexandra Carpentier (Cambridge)
Date: 
Wednesday, June 17, 2015 - 10:00am
Location: 
WIAS, Erhard-Schmidt-Saal, Mohrenstraße 39, 10117 Berlin

In this talk I will consider a general noisy linear regression setting Y = + \epsilon, that simultaneously describes the usual "vector" linear regression setting, and the "matrix" linear regression setting. I will consider the problem of inference in this model, i.e. estimation of the underlying parameter \theta, and associated uncertainty quantification.

TERES - Tail Event Risk managing Expected Shortfall

Speaker(s): 
Philipp Gschöpf (Humboldt-Universität zu Berlin)
Date: 
Monday, June 15, 2015 - 2:00pm
Location: 
Spandauer Straße 1, Room 23

A flexible framework for a tail event driven expected shortfall estimation is proposed. Our model allows to capture the risk associated with extreme (market) conditions. Connecting the implied tail thickness of a family of distributions with the quantile and expectile estimation, a platform for risk assessment is provided. Expected shortfall dynamics under different tail structure scenarios are investigated, particularly the implications of increased tail risk are discussed.

Localized Conditional Autoregressive Expectile Model

Speaker(s): 
Xiu Xu (Humboldt-Unverisität zu Berlin)
Date: 
Monday, June 15, 2015 - 2:00pm
Location: 
Spandauer Straße 1, Room 23

Localized conditional autoregressive expectile (CARE) model accounts for time-varying parameters in tail risk modelling. Our technique strikes a balance between parameter variability and the modelling bias resulting in potentially varying parameter homogeneity interval lengths. Over this intervals one can safely assume a parametric model in expectile estimation. Based on empirical evidence at three stock markets between 2005-2014 we show that CARE parameters vary over time and exhibit changing distributional properties.

Incorporating parameter risk into derivatives prices - an approach to bid-ask spreads

Speaker(s): 
Karl F. Bannör (Deloitte & Touche GmbH)
Date: 
Thursday, June 11, 2015 - 4:00pm
Location: 
TU Berlin, Straße des 17. Juni 136, 10623 Berlin, Raum MA 041

We present a new method based on convex risk measures to incorporate parameter risk (e.g. estimation and calibration risk) into derivative prices, generalizing the well-known conic finance approach. In this context, weak continuity properties of convex risk measures are discussed. As an application we calculate parameter risk-implied bid-ask spreads of exotics, enabling us to compare the parameter risk of different models and different exotics.

Middle Class Origins of the Financial Crisis

Speaker(s): 
Antoinette Schoar (Massachusetts Institute of Technology)
Date: 
Thursday, June 11, 2015 - 2:00pm
Location: 
Spandauer Straße 1, Room 23

We provide a novel interpretation of the debt dynamics leading up to the financial crisis of 2007. Earlier research suggests that distortions in the supply of mortgage credit, evidenced by a decoupling of credit flow from income growth, may have been responsible for the rise in house prices and the subsequent collapse of the housing market. This paper shows that the increase in mortgage originations was shared across the whole distribution of borrowers, and that middle and high income borrowers still made up the majority of originations at the peak of the boom.

On optimization aspects of finding Wasserstain(-Kantorovich) barycenter

Speaker(s): 
Aleksey Gasnikov (MITP, Moscow)
Date: 
Wednesday, June 10, 2015 - 10:00am
Location: 
WIAS, Raum 4.13, Hausvogteiplatz 11, 10117 Berlin

In the talk we'll discuss recent works by Marco Cuturi (Kyoto Univ.) et al. devoted to the fast algorithm of computation of Wasserstain barycenter (Wb). In our approach we try to reduce a problem to another high dimensional convex optimization problem . The idea is to freeze the measures support by allowing the cardinalities of the support sets to be large enough. Then we have to solve a sadle-point convex-concave optimization problem (Cuturi et al. considered this problem to be nonsmooth convex optimization problem). We propose new different numerical approaches to solve this problem. 1.

Gaussian processes and Bayesian moment estimation

Speaker(s): 
Anna Simoni
Date: 
Monday, June 1, 2015 - 2:00pm
Location: 
Spandauer Straße 1, Room 23

Chebyshev Interpolation for Parametric Option Pricing

Speaker(s): 
Kathrin Glau (Technische Universität München)
Date: 
Thursday, May 28, 2015 - 5:00pm
Location: 
TU Berlin, Straße des 17. Juni 136, 10623 Berlin, Raum MA 041

Function approximation with Chebyshev polynomials is a well-established and thoroughly investigated method within the field of numerical analysis. The method enjoys attractive convergence properties and its implementation is straightforward. We propose to apply tensorized Chebyshev interpolation to computing Parametric Option Prices (POP). This allows us to exploit the recurrent nature of the pricing problem in an efficient, reliable and general way.

Adaptive Testing on a Regression Function at a Point

Speaker(s): 
Timothy B. Armstrong (Yale University)
Date: 
Wednesday, May 27, 2015 - 10:00am
Location: 
WIAS, Erhard-Schmidt-Saal, Mohrenstraße 39, 10117 Berlin

We consider the problem of inference on a regression function at a point when the entire function satisfies a sign or shape restriction under the null. We propose a test that achieves the optimal minimax rate adaptively over a range of Hölder classes, up to a log log n term, which we show to be necessary for adaptation. We apply the results to adaptive one-sided tests for the regression discontinuity parameter under a monotonicity restriction, the value of a monotone regression function at the boundary, and the proportion of true null hypotheses in a multiple testing problem.

Pages

Subscribe to Research Seminars