Functional data analysis with application to periodically stimulated foetal heart rate data. I: Functional regression

Publisher Website
Google Scholar
Abstract
Functional regression is used to model longitudinal data where the number of measurements on the functional covariate is much greater than the number of subjects in the study. Thus, functional regression can be thought of as singular longitudinal analysis. We have modified existing functional regression techniques to the case of a functional covariate with a repeated stimulus. We applied this modified functional regression to periodically stimulated foetal heart rates. The heart rate tracings were used as a predictor of the child's psychomotor development at approximately 18 months of age. In the past, this type of data has been analysed using the partially subjective concept of habituation. By using the entire heart rate tracings through functional regression, we have the advantage that habituation does not need to be defined and all available information is used to predict later child development. Copyright © 2002 John Wiley & Sons, Ltd.