Official websites use .gov
A .gov website belongs to an official government organization in the United States.
Secure .gov websites use HTTPS
A lock (
) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.
Topics
Data & Maps
Surveys & Programs
Resource Library
Time Series Methods for Survey Estimation
Time Series Methods for Survey Estimation
RR87-20
Abstract
Papers by Scott and Smith (1974) and Scott, Smith, and Jones (1977) suggested the use of signal extraction results from time series analysis to improve estimates in periodic surveys. If the covariance structure of the usual survey estimators and their sampling errors is known, these results produce the linear functions of the usual estimators that have minimum mean squared error as estimators of the population values. Thus, current and past data are used in estimating the population quantity at the current time. To apply these results in practice one would identify and estimate a time series model for the time series of usual survey estimators, and estimate the covariance structure of the sampling errors over time using knowledge of the survey design. The paper reviews the theory behind this work, obtains some theoretical results on this approach, discusses some considerations involved in applying this approach, and reports on results obtained to date regarding practical application of these results to Census Bureau surveys.
Others in Series
Working Paper
A Comparison of Alternative Estimators for Revised Monthly Import S...
A Comparison of Alternative Estimators for Revised Monthly Import Statistics
Working Paper
Forecasting Age Specific Fertility Using Principal Components
Forecasting Age Specific Fertility Using Principal Components
Working Paper
It Doesn't Make Me Nearly as Cross: Some Advantages of the Point-Ve...
It Doesn't Make Me Nearly as Cross: Some Advantages of the Point-Vector Representation of Line Segments in Automated Cartography
Related Information
Page Last Revised - October 28, 2021
✕
Is this page helpful?
Yes
No
Yes
No✕
NO THANKS
255 characters maximum
255 characters maximum reached
255 characters maximum reached
✕
Thank you for your feedback.
Comments or suggestions?
Comments or suggestions?
