Chapter SEVEN. Application of Weighting with Probability Sampling and Nonresponse
Published Online: 11 AUG 2003
DOI: 10.1002/0471467979.ch7
Copyright © 2003 John Wiley & Sons, Inc.
Book Title
Quantitative Methods in Population Health: Extensions of Ordinary Regression
Additional Information
How to Cite
Palta, M. (2003) Application of Weighting with Probability Sampling and Nonresponse, in Quantitative Methods in Population Health: Extensions of Ordinary Regression, John Wiley & Sons, Inc., Hoboken, NJ, USA. doi: 10.1002/0471467979.ch7
Publication History
- Published Online: 11 AUG 2003
- Published Print: 15 AUG 2003
Book Series:
Book Series Editors:
- Walter A. Shewhart,
- Samuel S. Wilks
ISBN Information
Print ISBN: 9780471455059
Online ISBN: 9780471467977
- Summary
- Chapter
Keywords:
- sampling;
- complex survey;
- bias;
- probability sampling;
- inverse probability weight;
- empirical variance;
- Huber;
- non-response;
- missing data;
- MAR;
- MCAR
Summary
Unequal probability sampling leads to mean of sample being a biased estimator. Application of inverse probability weights to obtain unbiased estimators. Detailed presentation of how this works for estimation of mean. Example of unequal probability sampling to assemble sleep cohort, and inverse probability weights in PROC MIXED. Application of empirical variance to obtain standard errors.
Non-response as an example of unequal probability weights. Definition of missing completely at random and missing at random. Calculation of weights under assumption of missing at random. Recommendations for presenting data with non-response in publications. Application to follow-up study of very low birth weight to determine and analyze social function at age 5.
We discuss the issue of weighting versus adjustment by including the weighting variable as a covariate.