Online Program Home
My Program

Abstract Details

Activity Number: 665 - Regression Methods for Longitudinal Data
Type: Contributed
Date/Time: Thursday, August 1, 2019 : 10:30 AM to 12:20 PM
Sponsor: Section on Nonparametric Statistics
Abstract #304567
Title: Prediction Intervals for Out-Of-Sample Forecasts Based on Spline Extrapolation
Author(s): Jan Gertheiss*
Companies: Helmut Schmidt University
Keywords: Bootstrap; Functional Data; Gaussian Process; Generalized Additive Model

We consider the problem of predicting demand for specific products based on historic data. Due to substantial differences between products, a prediction model is fit for each product separately, using spline extrapolation. Employing a mixture of parametric and Gaussian process bootstrap, prediction intervals for future demand are derived. The idea is motivated and evaluated by real world data from automobile industry, which shows that the method developed is highly relevant for practical use such as supply chain management.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2019 program