Forecasting of density functions with an application to cross-sectional and intraday returns
By Piotr Kokoszka, Hong Miao, Alexander Petersen, Han Lin Shang. International Journal of Forecasting, 2019
58 citations recorded by the source corpus.
Abstract This paper is concerned with the forecasting of probability density functions. Density functions are nonnegative and have a constrained integral, and thus do not constitute a vector space. The implementation of established functional time series forecasting methods for such nonlinear data is therefore problematic. Two new methods are developed and compared to two existing methods. The comparison is based on the densities derived from cross-sectional and intraday returns. For such data, one of our new approaches is shown to dominate the existing methods, while the other is comparable to one of the existing approaches.
Subfields: Economics and Econometrics, Management Science and Operations Research
View Paper: https://www.semanticscholar.org/paper/96ca961c591f2f039bc5cf45f1b0b1a6f3e593e2
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Economics and Econometrics
- Victor M. Panaretos
- Laya Ghodrati
- Piotr Kokoszka
- H. Muller
- Chao Zhang
- Alexander Petersen
- Lajos Horv'ath
- Xianyang Zhang
In Management Science and Operations Research
Citations in the corpus
- Wasserstein Regression (2020, methodology): “, by the log quantile density (lqd) transformation (Petersen and Müller 2016) and then to employ functional regression models where the transformed functions serve as predictors and the responses are either also the transformed functions or scalars (Chen et al. 2019; Kokoszka et al. 2019; Petersen e”
- Distribution-on-Distribution Regression via Optimal Transport Maps (2021, background): “One approach to dealing with the non-linear nature of probability distributions is to apply a suitable transformation and map the problem back to a space with a linear structure [6, 3, 16, 7].”
- Wasserstein autoregressive models for density time series (2020, methodology): “We proceed to applying our WAR(1) model to real data sets and comparing its forecasting performance with that of four other density time series forecasting approaches, studied in Kokoszka et al. (2019), where they are introduced in great detail.”