arXiv subjects

Alexander Volkmann

Publications and source records attributed to Alexander Volkmann.

9 recordsLinked to original sources

arXiv2024

Generalized Multivariate Functional Additive Mixed Models for Location, Scale, and Shape

We propose a flexible regression framework to model the conditional distribution of multilevel generalized multivariate functional data of potentially mixed type, e.g. binary and continuous data. We make pointwise parametric distributional assumptions for each dimension of the multivariate functional data and model each distributional parameter as an additive function of covariates. The dependency between the different outcomes and, for multilevel functional data, also between different functions within a level is modelled by shared latent multivariate Gaussian processes. For a parsimonious representation of the latent processes, (generalized) multivariate functional principal components are estimated from the data and used as an empirical basis for these latent processes in the regression framework. Our modular two-step approach is very general and can easily incorporate new developments in the estimation of functional principal components for all types of (generalized) functional data. Flexible additive covariate effects for scalar or even functional covariates are available and are estimated in a Bayesian framework. We provide an easy-to-use implementation in the accompanying R package 'gmfamm' on CRAN and conduct a simulation study to confirm the validity of our regression framework and estimation strategy. The proposed multivariate functional model is applied to four dimensional traffic data in Berlin, which consists of the hourly numbers and mean speed of cars and trucks at different locations.

stat.ME↗

arXiv2023

Flexible joint models for multivariate longitudinal and time-to-event data using multivariate functional principal components

The joint modeling of multiple longitudinal biomarkers together with a time-to-event outcome is a challenging modeling task of continued scientific interest. In particular, the computational complexity of high dimensional (generalized) mixed effects models often restricts the flexibility of shared parameter joint models, even when the subject-specific marker trajectories follow highly nonlinear courses. We propose a parsimonious multivariate functional principal components representation of the shared random effects. This allows better scalability, as the dimension of the random effects does not directly increase with the number of markers, only with the chosen number of principal component basis functions used in the approximation of the random effects. The functional principal component representation additionally allows to estimate highly flexible subject-specific random trajectories without parametric assumptions. The modeled trajectories can thus be distinctly different for each biomarker. We build on the framework of flexible Bayesian additive joint models implemented in the R-package 'bamlss', which also supports estimation of nonlinear covariate effects via Bayesian P-splines. The flexible yet parsimonious functional principal components basis used in the estimation of the joint model is first estimated in a preliminary step. We validate our approach in a simulation study and illustrate its advantages by analyzing a study on primary biliary cholangitis.

stat.ME↗

arXiv2022

What Drives Inflation and How: Evidence from Additive Mixed Models Selected by cAIC

We analyze the forces that explain inflation using a panel of 122 countries from 1997 to 2015 with 37 regressors. 98 models motivated by economic theory are compared to a gradient boosting algorithm, non-linearities and structural breaks are considered. We show that the typical estimation methods are likely to lead to fallacious policy conclusions which motivates the use of a new approach that we propose in this paper. The boosting algorithm outperforms theory-based models. We confirm that energy prices are important but what really matters for inflation is their non-linear interplay with energy rents. Demographic developments also make a difference. Globalization and technology, public debt, central bank independence and political characteristics are less relevant. GDP per capita is more relevant than the output gap, credit growth more than M2 growth.

stat.AP↗

arXiv2021

Multivariate Functional Additive Mixed Models

Multivariate functional data can be intrinsically multivariate like movement trajectories in 2D or complementary like precipitation, temperature, and wind speeds over time at a given weather station. We propose a multivariate functional additive mixed model (multiFAMM) and show its application to both data situations using examples from sports science (movement trajectories of snooker players) and phonetic science (acoustic signals and articulation of consonants). The approach includes linear and nonlinear covariate effects and models the dependency structure between the dimensions of the responses using multivariate functional principal component analysis. Multivariate functional random intercepts capture both the auto-correlation within a given function and cross-correlations between the multivariate functional dimensions. They also allow us to model between-function correlations as induced by e.g.\ repeated measurements or crossed study designs. Modeling the dependency structure between the dimensions can generate additional insight into the properties of the multivariate functional process, improves the estimation of random effects, and yields corrected confidence bands for covariate effects. Extensive simulation studies indicate that a multivariate modeling approach is more parsimonious than fitting independent univariate models to the data while maintaining or improving model fit.

stat.ME↗

arXiv2020

On the Relationship between Treatment Effect Heterogeneity and the Variability Ratio Effect Size Statistic

Recently, the variability ratio (VR) effect size statistic has been used with increasing frequency in the study of differences in variation of a measured variable between two study populations. More specifically, the VR effect size statistic allows for the detection of treatment effect heterogeneity (TEH) of medical interventions. While a VR that is different from 1 is widely acknowledged to implicate a treatment effect heterogeneity (TEH) the exact relationship between those two quantities has not been discussed in detail thus far. In this note we derive a precise connection between TEH and VR. In particular, we derive precise upper and lower bounds on the TEH in terms of VR. Moreover, we provide an exemplary simulation for which VR is equal to 1 and there exist TEH. Our result has implications for the interpretation of VR effect size estimates regarding its connection to treatment effect heterogeneity of (medical) interventions.

stat.ME↗

arXiv2015

Isoperimetric structure of asymptotically conical manifolds

We study the isoperimetric structure of Riemannian manifolds that are asymptotic to cones with non-negative Ricci curvature. Specifically, we generalize to this setting the seminal results of G. Huisken and S.-T. Yau on the existence of a canonical foliation by volume preserving stable constant mean curvature surfaces at infinity of asymptotically flat manifolds as well as the results of the second-named author with S. Brendle and J. Metzger on the isoperimetric structure of asymptotically flat manifolds. We also include an observation on the isoperimetric cone angle of such manifolds. This result is a natural analogue of the positive mass theorem in this setting.

math.DG↗

arXiv2014

On the regularity of stationary points of a nonlocal isoperimetric problem

In this article we establish $C^{3,α}$-regularity of the reduced boundary of stationary points of a nonlocal isoperimetric problem in a domain $Ω\subset \mathbb{R}^n$. In particular, stationary points satisfy the corresponding Euler-Lagrange equation classically on the reduced boundary. Moreover, we show that the singular set has zero $(n-1)$-dimensional Hausdorff measure. This complements the results in Choksi & Sternberg, in which the Euler-Lagrange equation was derived under the assumption of $C^2$-regularity of the topological boundary and the results in Sternberg & Topaloglu in which the authors assume local minimality. In case $Ω$ has non-empty boundary, we show that stationary points meet the boundary of $Ω$ orthogonally in a weak sense, unless they have positive distance to it.

math.AP↗

arXiv2014

A monotonicity formula for free boundary surfaces with respect to the unit ball

We prove a monotonicity identity for compact surfaces with free boundaries inside the boundary of unit ball in $\mathbb R^n$ that have square integrable mean curvature. As one consequence we obtain a Li-Yau type inequality in this setting, thereby generalizing results of Oliveira and Soret, and Fraser and Schoen. In the final section of this paper we derive some sharp geometric inequalities for compact surfaces with free boundaries inside arbitrary orientable support surfaces of class $C^2$. Furthermore, we obtain a sharp lower bound for the $L^1$-tangent-point energy of closed curves in $\mathbb R^3$ thereby answering a question raised by Strzelecki, Szumańska and von der Mosel.

math.DG↗

arXiv2013

An Allard type regularity theorem for varifolds with Hölder continuous generalized normal

We prove that Allard's regularity theorem holds for rectifiable $n$-dimensional varifolds $V$ assuming a weaker condition on the first variation. This, in the special case when $V$ is a smooth manifold translates to the following: If $ω_n^{-1}ρ^{-n}{\rm area}(V\cap B_ρ(x))$ is sufficiently close to $1$ and the unit normal of $V$ satisfies a $C^{0,α}$ estimate, then $V\cap B_{ρ/2}(x)$ is the graph of a $C^{1,α}$ function with estimates. Furthermore, a similar boundary regularity theorem is true.

math.AP↗