• Home
  • Search
  • Online Randomized Distributionally Robust Forecast Combination for Dependent Data
  • https://doi.org/10.1111/jtsa.70056Copy DOI Icon

Online Randomized Distributionally Robust Forecast Combination for Dependent Data

Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

ABSTRACT We develop an online framework for forecast combination that integrates distributional robustness with randomized weights in dependent time‐series settings. Unlike deterministic approaches that update a single weight vector, our approach models the weights as random draws from parametric families, with parameters updated sequentially to minimize a worst‐case expected loss over a Wasserstein ambiguity set centered at the empirical joint distribution of forecasts and realizations. Randomization facilitates adaptive exploration of alternative weight configurations and improves calibration by accounting for combination uncertainty, while distributional robustness provides protection against heavy tails and model misspecification. We establish finite‐sample concentration bounds for ‐mixing processes, derive oracle‐type excess risk and online regret guarantees, and characterize the bias‐variance trade‐off induced by randomization. In addition, we show that a batch version of the estimator is asymptotically normal under standard identification and mixing conditions. Monte Carlo experiments across a variety of data‐generating processes demonstrate that the proposed method achieves lower worst‐case error, faster post‐break adjustment, and improved predictive coverage relative to existing forecast combination methods. An empirical application to macroeconomic forecasting further illustrates its robustness and effectiveness under dependence and evolving dynamics.

Similar Papers
  • Conference Article
  • Citations9

Optimal combined load forecast based on the improved analytic hierarchy process

  • Dec 10, 2002
  • Zhou Ren-Jun +1
  • PDF
  • Research Article
  • Citations4

THE APPLICATION OF RIDGE REGRESSION METHODS WHEN COMBINING FORECASTS

  • Oct 03, 2018
  • Finance: Theory and Practice
  • A A Frenkel’ +3
  • Research Article
  • Citations10

Forecast Combination for Euro Area Inflation: A Cure in Times of Crisis?

  • Jan 24, 2017
  • Journal of Forecasting
  • Kirstin Hubrich +1
  • Research Article

THE IMPACT OF COVID-19 ON PASSENGER SHIPPING ACTIVITIES IN SELECTED EU COUNTRIES: DIAGNOSIS AND LONG-TERM SCENARIOS

  • Sep 01, 2025
  • Scientific Journal of Silesian University of Technology. Series Transport
  • Agnieszka Barczak +2
  • Conference Article
  • Citations6

A nonlinear combining forecast method based on fuzzy neural network

  • Nov 04, 2002
  • Jing-Rong Dong
  • Research Article
  • Citations10

An extreme bias-penalized forecast combination approach to commodity price forecasting

  • Oct 17, 2022
  • Information Sciences
  • Yifei Zhang +3
  • Research Article
  • Citations108

Distributions of forecasting errors of forecast combinations: Implications for inventory management

  • Mar 31, 2016
  • International Journal of Production Economics
  • Devon K Barrow +1
  • Conference Article
  • Citations3

Application of Combination Forecasting Based on Rough Sets Theory on Electric Power System

  • Jan 01, 2006
  • Yidan Bao +4
  • Conference Article
  • Citations8

Application of self-organizing combination forecasting method in power load forecast

  • Jan 01, 2007
  • Wei Sun +1
  • Conference Article
  • Citations9

Symbolic interval time series forecasting using a hybrid model

  • Oct 01, 2006
  • Andre S Maia +2
  • Research Article
  • Citations19

On the nonlinear and nonnormal filter using rejection sampling

  • Jan 01, 1999
  • IEEE Transactions on Automatic Control
  • H Tanizaki
  • Conference Article
  • Citations1

Short-term Load Forecasting Considering Demand Response

  • Dec 23, 2021
  • Huang Kechang +1
  • Book Chapter
  • Citations1

Combining Stock Market Volatility Forecasts with Analysis of Stock Materials under Regime Switching

  • Jan 01, 2011
  • Dong Jing-Rong +2
  • Research Article
  • Citations78

Load probability density forecasting by transforming and combining quantile forecasts

  • Aug 04, 2020
  • Applied Energy
  • Shu Zhang +4
  • Research Article

Modeling CO<sub>2</sub> Emissions of Top 5 Emitters with Combination Technique

  • Dec 01, 2012
  • Advanced Materials Research
  • Wei Sun +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.