Abstract
AbstractResponse functions that link regression predictors to properties of the response distribution are fundamental components in many statistical models. However, the choice of these functions is typically based on the domain of the modeled quantities and is usually not further scrutinized. For example, the exponential response function is often assumed for parameters restricted to be positive, although it implies a multiplicative model, which is not necessarily desirable or adequate. Consequently, applied researchers might face misleading results when relying on such defaults. For parameters restricted to be positive, we propose to construct alternative response functions based on the softplus function. These response functions are differentiable and correspond closely to the identity function for positive values of the regression predictor implying a quasi-additive model. Consequently, the proposed response functions allow for an additive interpretation of the estimated effects by practitioners and can be a better fit in certain data situations. We study the properties of the newly constructed response functions and demonstrate the applicability in the context of count data regression and Bayesian distributional regression. We contrast our approach to the commonly used exponential response function.
Funder
Deutsche Forschungsgemeinschaft
National Bank of Belgium
Georg-August-Universität Göttingen
Publisher
Springer Science and Business Media LLC
Subject
Statistics, Probability and Uncertainty,Statistics and Probability
Reference42 articles.
1. Abramowitz M, Stegun IA (1972) Handbook of mathematical functions. Number 55 in National Bureau of Standards: Applied Mathematics, 10 edn. U.S. Government Printing Office, Washington
2. Agresti A (2013)Categorical data analysis. Number 792 in Wiley Series in Probability and Statistics, 3 edn. Wiley, Hoboken, ISBN 978-0-470-46363-5
3. Bacon DW, Watts DG (1971) Estimating the transition between two intersecting straight lines. Biometrika 58(3):525–534
4. Bader B, Yan J, Zhang X (2018) Automated threshold selection for extreme value analysis via ordered goodness-of-fit tests with adjustment for false discovery rate. Ann Appl Stat 12(1):310–329
5. Bee M, Dupuis DJ, Trapin L (2019) Realized peaks over threshold: a time-varying extreme value approach with high-frequency-based measures. J Financ Economet 17(2):254–283