Fast calibrated additive quantile regression

Abstract

We propose a novel framework for fitting additive quantile regression models, which provides well calibrated inference about the conditional quantiles and fast automatic estimation of the smoothing parameters, for model structures as diverse as those usable with distributional GAMs, while maintaining equivalent numerical efficiency and stability. The proposed methods are at once statistically rigorous and computationally efficient, because they are based on the general belief updating framework of Bissiri et al. (2016) to loss based inference, but compute by adapting the stable fitting methods of Wood et al. (2016). We show how the pinball loss is statistically suboptimal relative to a novel smooth generalisation, which also gives access to fast estimation methods. Further, we provide a novel calibration method for efficiently selecting the 'learning rate' balancing the loss with the smoothing priors during inference, thereby obtaining reliable quantile uncertainty estimates. Our work was motivated by a probabilistic electricity load forecasting application, used here to demonstrate the proposed approach. The methods described here are implemented by the qgam R package, available on the Comprehensive R Archive Network (CRAN).

References in corpus (3)

• Smoothing parameter and model selection for general smooth models
• A General Framework for Updating Belief Distributions
• Smoothed estimating equations for instrumental variables quantile regression

Cited by in corpus (11)

• Interpretable Machine Learning -- A Brief History, State-of-the-Art and Challenges
• Classifier Calibration: A survey on how to assess and improve predicted class probabilities
• Gratia: An R package for exploring generalized additive models
• Probabilistic Forecasting of Regional Net-load with Conditional Extremes and Gridded NWP
• Potential for allocative harm in an environmental justice data tool
• Multivariate Simulation-based Forecasting for Intraday Power Markets: Modelling Cross-Product Price Effects
• Investigating differences in lab-quality and remote recording methods with dynamic acoustic measures
• Improved inference on risk measures for univariate extremes
• Quantile regression for longitudinal functional data with application to feed intake of lactating sows
• Non-conjugate variational Bayes for pseudo-likelihood mixed effect models
• An utopic adventure in the modelling of conditional univariate and multivariate extremes