Establishing an optimal sampling schedule is a crucial step toward a precise inference of the underlying functional mechanism of a process, especially when data collection is expensive/difficult. This work is concerned with optimal sampling plans for predicting a scalar response using a functional predictor when a quadratic regression relationship is present. An optimality criterion for selecting the best sampling schedules is derived, and some important properties of the criterion are provided. In addition, a bootstrap aggregating (bagging) strategy is proposed to enhance the quality of the obtained sampling schedule.
- Functional data analysis
- Functional principal component
- Functional regression model
ASJC Scopus subject areas
- Statistics and Probability