Probabilistic Time Series Forecasts with Autoregressive Transformation Models

DOI10.48550/ARXIV.2110.08248zbMATH Open1516.62028arXiv2110.08248OpenAlexW4319234957MaRDI QIDQ88049FDOQ88049

Authors: David Rügamer, Philipp F. M. Baumann, Thomas Kneib, Torsten Hothorn, David Rügamer, Philipp F. M. Baumann, Thomas Kneib 

Publication date: 15 October 2021

Published in: Statistics and Computing (Search for Journal in Brave)

Abstract: Probabilistic forecasting of time series is an important matter in many applications and research fields. In order to draw conclusions from a probabilistic forecast, we must ensure that the model class used to approximate the true forecasting distribution is expressive enough. Yet, characteristics of the model itself, such as its uncertainty or its feature-outcome relationship are not of lesser importance. This paper proposes Autoregressive Transformation Models (ATMs), a model class inspired by various research directions to unite expressive distributional forecasts using a semi-parametric distribution assumption with an interpretable model specification. We demonstrate the properties of ATMs both theoretically and through empirical evaluation on several simulated and real-world forecasting datasets.

Full work available at URL: https://arxiv.org/abs/2110.08248

Recommendations

• Prediction-based adaptive compositional model for seasonal time series analysis
• Generative exponential smoothing and generative ARMA models to forecast time-variant rates or probabilities
• Semiparametric distribution forecasting
• Generalizing the Theta method for automatic forecasting
• A flexible univariate autoregressive time-series model for dispersed count data

zbMATH Keywords

distributional regressionconditional density estimationnormalizing flowssemiparametric models

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08) Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Inference from stochastic processes and prediction (62M20)

Cites Work

• Neural autoregressive distribution estimation
• Probabilistic Forecasts, Calibration and Sharpness
• Quantile regression.
• On a Mixture Autoregressive Model
• Stationary vine copula models for multivariate time series
• On the invertibility of time series models
• Distributional regression forests for probabilistic precipitation forecasting in complex terrain
• Transformation boosting machines
• Machine learning. A probabilistic perspective
• Nonparametric Estimation of Conditional Distributions and Rank-Tracking Probabilities With Time-Varying Transformation Models in Longitudinal Studies
• Title not available (Why is that?)
• The Bernstein polynomial basis: a centennial retrospective
• Most likely transformations
• Title not available (Why is that?)
• Title not available (Why is that?)
• Learning transformation models for ranking and survival analysis
• Inference on counterfactual distributions
• Conditional Transformation Models
• Multivariate conditional transformation models

Cited In (6)

• AA-forecast: anomaly-aware forecast for extreme events
• Forward and reversed time prediction of autoregressive sequences
• Time series modeling and forecasting by mathematical programming
• Generative exponential smoothing and generative ARMA models to forecast time-variant rates or probabilities
• deeptrafo
• Autoregressive prediction with rolling mechanism for time series forecasting with small sample size

This page was built for publication: Probabilistic Time Series Forecasts with Autoregressive Transformation Models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q88049)