Publications (61)52.65 Total impact
 [Show abstract] [Hide abstract]
ABSTRACT: In this note we prove the following law of the iterated logarithm for the Grenander estimator of a monotone decreasing density: If $f(t_0) > 0$, $f'(t_0) < 0$, and $f'$ is continuous in a neighborhood of $t_0$, then \begin{eqnarray*} \limsup_{n\rightarrow \infty} \left ( \frac{n}{2\log \log n} \right )^{1/3} ( \widehat{f}_n (t_0 )  f(t_0) ) = \left f(t_0) f'(t_0)/2 \right^{1/3} 2M \end{eqnarray*} almost surely where $ M \equiv \sup_{g \in {\cal G}} T_g = (3/4)^{1/3}$ and $ T_g \equiv \mbox{argmax}_u \{ g(u)  u^2 \} $; here ${\cal G}$ is the twosided Strassen limit set on $R$. The proof relies on laws of the iterated logarithm for local empirical processes, Groeneboom's switching relation, and properties of Strassen's limit set analogous to distributional properties of Brownian motion. 
Article: Confidence Bands for Distribution Functions: A New Look at the Law of the Iterated Logarithm
[Show abstract] [Hide abstract]
ABSTRACT: We present a general law of the iterated logarithm for stochastic processes on the open unit interval having subexponential tails in a locally uniform fashion. It applies to standard Brownian bridge but also to suitably standardized empirical distribution functions. This leads to new goodnessoffit tests and confidence bands which refine the procedures of Berk and Jones (1979) and Owen (1995). Roughly speaking, the high power and accuracy of the latter procedures in the tail regions of distributions are esentially preserved while gaining considerably in the central region.  [Show abstract] [Hide abstract]
ABSTRACT: We present new algorithms for $M$estimators of multivariate location and scatter and for symmetrized $M$estimators of multivariate scatter. The new algorithms are considerably faster than currently used fixedpoint and other algorithms. The main idea is to utilize a Taylor expansion of second order of the target functional and devise a partial NewtonRaphson procedure. In connection with the symmetrized $M$estimators we work with incomplete $U$statistics to accelerate our procedures initially.  [Show abstract] [Hide abstract]
ABSTRACT: This survey provides a selfcontained account of Mestimation of multivariate location and scatter, with special emphasis on maximum likelihood estimation for multivariate tdistributions. In particular, we present new proofs for existence of the underlying Mfunctionals, and discuss their weak continuity and differentiability. Moreover, we present Mestimation of scatter in a rather general framework with matrixvalued random variables. By doing so we reveal a connection between Tyler's (1987) Mfunctional of scatter and the estimation of proportional covariance matrices. Moreover, this general framework allows us to treat a new class of scatter estimators, based on symmetrizations of arbitrary order.  [Show abstract] [Hide abstract]
ABSTRACT: We consider nonparametric maximumlikelihood estimation of a logconcave density in case of intervalcensored, rightcensored and binned data. We allow for the possibility of a subprobability density with an additional mass at +∞, which is estimated simultaneously. The existence of the estimator is proved under mild conditions and various theoretical aspects are given, such as certain shape and consistency properties. An EM algorithm is proposed for the approximate computation of the estimator and its performance is illustrated in two examples.Electronic Journal of Statistics 11/2013; 8(1). DOI:10.1214/14EJS930 · 1.02 Impact Factor  [Show abstract] [Hide abstract]
ABSTRACT: In the setting of highdimensional linear models with Gaussian noise, we investigate the possibility of confidence statements connected to model selection. Although there exist numerous procedures for adaptive (point) estimation, the construction of adaptive confidence regions is severely limited (cf. Li in Ann Stat 17:1001–1008, 1989). The present paper sheds new light on this gap. We develop exact and adaptive confidence regions for the best approximating model in terms of risk. One of our constructions is based on a multiscale procedure and a particular coupling argument. Utilizing exponential inequalities for noncentral χ 2distributions, we show that the risk and quadratic loss of all models within our confidence region are uniformly bounded by the minimal risk times a factor close to one.Probability Theory and Related Fields 01/2013; 155(34). DOI:10.1007/s0044001204147 · 1.46 Impact Factor 
Conference Paper: An analysis of variance type method to describe and compare steady states in clinical data
[Show abstract] [Hide abstract]
ABSTRACT: Identifying and comparing different steady states is an important task for clinical decision making. Data from unequal sources, comprising diverse patient status information, have to be interpreted. In order to compare results an expressive representation is the key. In this contribution we suggest a criterion to calculate a contextsensitive value based on variance analysis and discuss its advantages and limitations referring to a clinical data example obtained during anesthesia. Different drug plasma target levels of the anesthetic propofol were preset to reach and maintain clinically desirable steady state conditions with target controlled infusion (TCI). At the same time systolic blood pressure was monitored, depth of anesthesia was recorded using the bispectral index (BIS) and propofol plasma concentrations were determined in venous blood samples. The presented analysis of variance (ANOVA) is used to quantify how accurately steady states can be monitored and compared using the three methods of measurement.EHealth and Bioengineering Conference (EHB), 2013; 01/2013 
Conference Paper: Trend detection in timeseries data of propofol concentration in breath
Society for Technology in Anesthesia  STA 2013 Annual Meeting, Phoenix, Arizona, USA; 01/2013  Journal of the American Statistical Association 09/2011; 106(495):919919. DOI:10.1198/jasa.2011.tm11316 · 2.11 Impact Factor
 [Show abstract] [Hide abstract]
ABSTRACT: We derive multiscale statistics for deconvolution in order to detect qualitative features of the unknown density. An important example covered within this framework is to test for local monotonicity on all scales simultaneously. We investigate the moderately illposed setting, where the Fourier transform of the error density in the deconvolution model is of polynomial decay. For multiscale testing, we consider a calibration, motivated by the modulus of continuity of Brownian motion. We investigate the performance of our results from both the theoretical and simulation based point of view. A major consequence of our work is that the detection of qualitative features of a density in a deconvolution problem is a doable task although the minimax rates for pointwise estimation are very slow.The Annals of Statistics 07/2011; 41(3). DOI:10.1214/13AOS1089 · 2.44 Impact Factor  [Show abstract] [Hide abstract]
ABSTRACT: Let $P$ be a probability distribution on $q$dimensional space. The socalled DiaconisFreedman effect means that for a fixed dimension $d << q$, most $d$dimensional projections of $P$ look like a scale mixture of spherically symmetric Gaussian distributions. The present paper provides necessary and sufficient conditions for this phenomenon in a suitable asymptotic framework with increasing dimension $q$. It turns out, that the conditions formulated by Diaconis and Freedman (1984) are not only sufficient but necessary as well. Moreover, letting $\hat{P}$ be the empirical distribution of $n$ independent random vectors with distribution $P$, we investigate the behavior of the empirical process $\sqrt{n}(\hat{P}  P)$ under random projections, conditional on $\hat{P}$.  [Show abstract] [Hide abstract]
ABSTRACT: This paper introduces and analyzes a stochastic search method for parameter estimation in linear regression models in the spirit of Beran and Millar (1987). The idea is to generate a random finite subset of a parameter space which will automatically contain points which are very close to an unknown true parameter. The motivation for this procedure comes from recent work of Duembgen, Samworth and Schuhmacher (2011) on regression models with logconcave error distributions.  [Show abstract] [Hide abstract]
ABSTRACT: We derive multiscale statistics for deconvolution in order to detect qualitative features of the unknown density. An important example covered within this framework is to test for local monotonicity on all scales simultaneously. The errors in the deconvolution model are restricted to a certain class of distributions that include Laplace, Gamma and Exponential random variables. Our approach relies on inversion formulas for deconvolution operators. For multiscale testing, we consider a calibration, motivated by the modulus of continuity of Brownian motion. We investigate the performance of our results from both the theoretical and simulation based point of view. A major consequence of our work is that the detection of qualitative features of a density in a deconvolution problem is a doable task although the minimax rates for pointwise estimation are very slow.  [Show abstract] [Hide abstract]
ABSTRACT: We review various inequalities for Mills' ratio (1  \Phi)/\phi, where \phi and \Phi denote the standard Gaussian density and distribution function, respectively. Elementary considerations involving finite continued fractions lead to a general approximation scheme which implies and refines several known bounds.  [Show abstract] [Hide abstract]
ABSTRACT: This note proves Hellingerconsistency for the nonparametric maximum likelihood estimator of a logconcave probability density on .Statistics [?] Probability Letters 03/2010; 80(56):376380. DOI:10.1016/j.spl.2009.11.013 · 0.53 Impact Factor  [Show abstract] [Hide abstract]
ABSTRACT: We study the approximation of arbitrary distributions $P$ on $d$dimensional space by distributions with logconcave density. Approximation means minimizing a KullbackLeiblertype functional. We show that such an approximation exists if and only if $P$ has finite first moments and is not supported by some hyperplane. Furthermore we show that this approximation depends continuously on $P$ with respect to Mallows distance $D_1(\cdot,\cdot)$. This result implies consistency of the maximum likelihood estimator of a logconcave density under fairly general conditions. It also allows us to prove existence and consistency of estimators in regression models with a response $Y=\mu(X)+\epsilon$, where $X$ and $\epsilon$ are independent, $\mu(\cdot)$ belongs to a certain class of regression functions while $\epsilon$ is a random error with logconcave density and mean zero.The Annals of Statistics 02/2010; 39(2). DOI:10.1214/10AOS853 · 2.44 Impact Factor 
Article: Nemirovski's Inequalities Revisited
[Show abstract] [Hide abstract]
ABSTRACT: An important tool for statistical research are moment inequalities for sums of independent random vectors. Nemirovski and coworkers (1983, 2000) derived one particular type of such inequalities: For certain Banach spaces $(\B,\\cdot\)$ there exists a constant $K = K(\B,\\cdot\)$ such that for arbitrary independent and centered random vectors $X_1, X_2, ..., X_n \in \B$, their sum $S_n$ satisfies the inequality $ E \S_n \^2 \le K \sum_{i=1}^n E \X_i\^2$. We present and compare three different approaches to obtain such inequalities: Nemirovski's results are based on deterministic inequalities for norms. Another possible vehicle are type and cotype inequalities, a tool from probability theory on Banach spaces. Finally, we use a truncation argument plus Bernstein's inequality to obtain another version of the moment inequality above. Interestingly, all three approaches have their own merits.The American Mathematical Monthly 02/2010; 117(2):138160. DOI:10.4169/000298910X476059 · 0.32 Impact Factor  [Show abstract] [Hide abstract]
ABSTRACT: In diesem Kapitel betrachten wir das einfache Modell unabhängiger, identisch verteilter Zufallsvariablen X1, X2, …, Xn mit Wertebereich X und unbekannter Verteilung P; siehe Abschnitt 3.2. 
Article: Statistische Tests
[Show abstract] [Hide abstract]
ABSTRACT: Anhand von Beispiel 1.2 illustrieren wir nun ein wichtiges statistisches Verfahren, nämlich Fishers exakten Test, und erläutern relevante Grundbegriffe des Testens. Die zugrundeliegenden allgemeinen Konzepte und Beweise werden dann in späteren Abschnitten präsentiert.  [Show abstract] [Hide abstract]
ABSTRACT: Erfahrungsgemäß kann man viele (empirische) Verteilungsfunktionen durch Normalverteilungsfunktionen approximieren. Dies legt nahe, sich statistische Verfahren für diese Verteilungsfamilie zu überlegen. Historisch gesehen waren dies sogar die ersten statistischen Verfahren. In diesem Kapitel betrachten wir eine Stichprobe X = (Xi )i = 1n X = (X_i )_{i = 1}^n von stochastisch unabhängigen, nach N (μ,σ2) verteilten Zufallsvariablen. Dabei sind µ ∈ ℝ und σ > 0 Parameter, von denen mindestens einer unbekannt ist und durch ein Konfidenzintervall eingegrenzt werden soll.
Publication Stats
790  Citations  
52.65  Total Impact Points  
Top Journals
Institutions

2003–2013

Universität Bern
 Institute of Mathematical Statistics and Actuarial Science
Berna, Bern, Switzerland


2011

Technische Universität Dresden
Dresden, Saxony, Germany


2009

University of Tampere
Tammerfors, Province of Western Finland, Finland


2008

University of Cambridge
Cambridge, England, United Kingdom


1996–2007

Stanford University
Palo Alto, California, United States


2006

Lomonosov Moscow State University
Moskva, Moscow, Russia


1998–2003

Universität zu Lübeck
 Institut für Mathematik
Lübeck Hansestadt, SchleswigHolstein, Germany


1994–1998

Universität Heidelberg
 Institute of Applied Mathematics
Heidelburg, BadenWürttemberg, Germany
