U.S. flag

An official website of the United States government

Skip Header


Modeling Survey Time Series Data with Flow-Observed CARMA Processes

Written by:
RRS2023-08

Abstract

Published survey data often are delivered as estimates computed over an epoch of time. Customers may desire to obtain survey estimates corresponding to epochs, or time points, that differ from the published estimates. This “change of support” problem can be addressed through the use of continuous time models of the underlying population process, while taking into account the sampling error that survey data is subject to. The application of a Continuous Auto Regressive Moving Average (CARMA) model is investigated as a tool to provide change of support applications, thereby allowing both interpolation and shrinkage for published survey estimates. A simulation study provides comparisons of competing estimation methods, and a synthetically constructed data set is developed in order to elucidate real data applications. The proposed method can be successful for change of support problems, despite modeling challenges with the CARMA framework.

Page Last Revised - October 17, 2023
Is this page helpful?
Thumbs Up Image Yes Thumbs Down Image No
NO THANKS
255 characters maximum 255 characters maximum reached
Thank you for your feedback.
Comments or suggestions?

Top

Back to Header