At the Edge of Donsker's Theorem: Asymptotics of Multiscale Scan Statistics

EI Seminar
The Erasmus University, Rotterdam Campus

Bandwidth selection is a critical aspect of statistical tests based on nonparametric regression or density estimation, and multiscale test procedures address this issue by incorporating all bandwidths simultaneously.

Speaker
Fabian Mies
Date
Thursday 10 Apr 2025, 12:00 - 13:00
Type
Seminar
Room
ET-14
Location
Campus Woudestein
Add to calendar

Remarkably, this approach avoids a severe multiple testing penalty and instead offers a "free lunch" in statistical inference: the test achieves asymptotically optimal detection power across all scales without prior knowledge of the effect's length scale.

However, constructing valid multiscale procedures is highly dependent on the sampling setting and often relies on bounding unknown and difficult-to-identify quantities, such as exponential tail bounds.

In this work, we demonstrate how to obtain a feasible multiscale test for a broad range of sampling settings via weak convergence arguments, by replacing the additive multiscale penalty with a multiplicative weighting. Specifically, we derive tightness conditions for the functional central limit in Hölder spaces with a critical modulus of continuity, where Donsker's theorem fails to hold.

Probabilistically, we discover a novel form of restricted weak convergence that holds only in the tail of the distribution. This new theoretical foundation preserves the optimal detection properties of multiscale tests and extends their applicability to nonstationary nonlinear time series via a tailored bootstrap scheme. 

Applications to signal discovery, goodness-of-fit testing of regression functions, and multiple changepoint detection are studied in detail.By offering a fresh perspective on multiscale statistics, we aim to facilitate their adaptation to a broader range of statistical problems.

See also

Overparametrisation and the Bias-variance Dilemma

Johannes Schmidt-Hieber (University of Twente)
Person writing on a whiteboard

Inference in Time-Varying SVARs Identified with Sign Restrictions

Jonas Arias (Federal Reserve Bank of Philadelphia)
cropped view of man getting US dollars out of a wallet

A Smaller Cycle Formulation for Periodic Event Scheduling Problems

Rolf van Lieshout (Eindhoven University of Technology)
Image - Swiss Train

Systemic Risk: CoVaR, Comovement, and Portfolio Selection

Liang Peng (Georgia State University)
The Erasmus University, Rotterdam Campus

Research Workshop on Inference and Optimality in Econometrics

Keynote Speaker: Isaiah Andrews
Image - Workshop Inference and Optimality in Econometrics

Lecture Asymptotic Optimality in Econometrics

Isaiah Andrews (Massachusetts Institute of Technology)
Image - Isaiah-Andrews

Bounds of the Market Risk Premium

Jens Jackwerth (University of Konstanz)
A person jumping off from gray concrete building

FinEML Conference 2025

Financial Econometrics Meets Machine Learning
Google Deep mind
More information

Do you want to know more about the event? Contact the secretariat Econometrics at eb-secr@ese.eur.nl.

Compare @count study programme

  • @title

    • Duration: @duration
Compare study programmes