AAPOR
The leading association
of public opinion and
survey research professionals
American Association for Public Opinion Research

Webinar Details

Non-probability Sampling for Finite Population Inference

Jill Dever and Richard Valliant

Tuesday, October 18, 2016
12:00 - 1:30 PM CDT/ 1:00 - 2:30 PM EDT/ 10:00 - 11:30 AM PDT

ASA-SRMS members will receive AAPOR member pricing on webinars when registering for live webinars or purchasing recordings of webinars.
If you are an ASA member, click here to purchase.

Purchase a recording of this webinar nowPreview webinar recording

About This Course:


Although selecting a probability sample has been the standard for decades for making inferences from a sample to a finite population, incentives are increasing to use data obtained without a defined sampling mechanism, i.e., non-probability samples. In a world of “big data”, large amounts of data are readily available through methods that are faster and need fewer resources relative to most probability-based designs.  There are many ways of collecting data now without a pre-specified sampling design—volunteer web panels, tele-voting, expert selection, respondent-driven network sampling, and others—none of which require probability samples. 
 
Design-based inference, in which population values are estimated through the random sampling procedure specified by the sampler, cannot be used for non-probability samples. One alternative is quasi-randomization where pseudo-inclusion probabilities (referred to as propensity scores) are estimated from covariates available for both sample and nonsample units. Another estimation approach is superpopulation modeling; analytic variables collected on the sample units are used in a model to predict values for the nonsample units. Variances of estimators can be computed using replication methods or approaches derived using modelling. We include several simulation studies to illustrate the properties of these approaches and discuss the pros and cons of each.  
 

Learning Objectives:

  1. Understand the different types of non-probability samples currently in use
  2. Understand how non-probability samples can be affected by coverage errors, nonresponse, and measurement errors
  3. Understand what methods of estimation can be used for non-probability samples and the arguments used to justify them
 

About the Instructor:


Dr. Richard L. Valliant is a Research Professor at the University of Michigan and the Joint Program for Survey Methodology at the University of Maryland.  He has over 40 years of experience in survey sampling, estimation theory, and statistical computing.  He was formerly an Associate Director at Westat and a mathematical statistician with the Bureau of Labor Statistics.  He has a range of applied experience in survey estimation and sample design on a variety of establishment and household surveys.  He is also a Fellow of the American Statistical Association and has been an editor of the Journal of the American Statistical Association, the Journal of Official Statistics, and Survey Methodology.
 
Dr. Jill A. Dever is a Senior Research Statistician in the Washington, DC office of RTI International. She has over 20 years of survey research experience related to sampling design, weighting and data analysis in various subject areas such as health and health care, the U.S. military, and education.  She was a member of the 2013 AAPOR task force charged with reporting on issues related to non-probability sampling.  To date, she has co-authored three books including Practical Tools for Designing and Weighting Sample Surveys with Drs. Valliant and Kreuter.  She is also a Fellow of the American Statistical Association. 

 

This webinar is sponsored by Nielsen_ColourLogo2_small.jpg