Skip to main content
Skip to main menu


Some methods for functional econometric time series

Piotr Kokoszka
Colorado State University
Room 306, Statistics Building 1130

The talk will introduce fundamental ideas of the analysis of time series of functions. Examples of such time series are yield curves and intraday return curves. Within the framework of functional data analysis, fundamental concept of long-run covariance, autocorrelations and their estimators will be introduced. Three specific inferential problems will be discussed: (1) testing if a functional time series is stationary, (2) testing if it is a functional weak white noise, (3) detecting change points in its mean structure in the presence of changing variability. An asymptotic framework as well as numerical implementation will be outlined.

Support us

We appreciate your financial support. Your gift is important to us and helps support critical opportunities for students and faculty alike, including lectures, travel support, and any number of educational events that augment the classroom experience. Click here to learn more about giving.

Every dollar givenĀ has a direct impact upon ourĀ students and faculty.