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

Webinar Details

Practical Guide for Surveys Based on Nonprobability Samples

Mansour Fahimi, Frances Barlas, Randall Thomas

Tuesday, February 13, 2018
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 now

Registration works best using Chrome or Firefox.


NOTE: If you purchased the yearly webinar subscription with your membership renewal, you are already registered for this webinar and do not need to re-register. You will automatically receive the login instructions prior to the event. Click here for the Webinar Package FAQs.


About This Course:

The times, they are a-changing! Traditional probability-based sampling techniques require a number of fundamental, yet increasingly unattainable, assumptions. Briefly, without a complete sampling frame and a data collection protocol that can secure high response rates, the available inferential machinery can break down. These difficulties, along with the escalating costs of probability-based methods, have prompted many researchers to consider nonprobability samples as practical alternatives. This webinar provides concrete recommendations for working with different nonprobability samples based on our years of hands-on experience. We will begin with an overview of different types of nonprobability samples and discuss their pros and cons from a fitness for use perspective. Focusing on online surveys, we will cover best practices for sourcing and selection of such samples, including effective options for sample balancing, incentive options, and considerations for data quality given the vast and varied landscape of sample providers.   Lastly, we will lay the foundation for our next webinar on robust weighting and calibration methodologies that can reduce some of the inherent biases of such samples, as well as optimal methods for blending probability and nonprobability samples. We will end this webinar with some contemplations about the new directions in survey sampling in the digital age.
 

Webinar Level:
Introductory

 

 

Learning Objectives:

   
  • Demystifying nonprobability samples and their pragmatic utilities
  • Reviewing best practices for nonprobability sample sourcing and selection methodologies
  • Identifying and dealing with the hidden hazards of nonprobability samples

About the Instructors:

 
Mansour Fahimi, Frances Barlas, and Randall Thomas

Mansour Fahimi, Ph.D., Chief Statistician & Senior Vice President
With over 25 years of experience in survey and market research methods and applications, Dr. Mansour Fahimi is the Senior Vice President and Chief Statistician at GfK Custom Research, LLC. Mansour works on design and administration of complex surveys, as well as optimization techniques in sampling, post-survey data enhancement procedures including nonresponse bias analysis, imputation of missing data, computation of survey weights, and methods for variance estimation. As a leading researcher in telephone and address-based sampling methods, he has worked on refinements for improving the coverage and inferential possibilities of surveys employing these methods. He has extensive experience with data analysis involving multivariate techniques, time series, nonparametric methods, and procedures for analysis of data from complex surveys. In recent years, Mansour has been working on non-probability sampling alternatives and his research and publications are now focused on improving the integrity of data from surveys that are subject to high rates of undercoverage and nonresponse.
 
Frances M. Barlas, Ph.D., Senior Research Scientist & Vice President
With over 15 years of experience in survey research, Dr. Frances Barlas is a leading survey methodologist in online surveys. She conducts research-on-research to improve all aspects of survey methodology at GfK Custom Research, focusing on survey sampling, weighting, and measurement. Frances also leads research and development initiatives to advance the operational efficiency and statistical integrity of GfK’s KnowledgePanel® and other GfK research assets. Her recent research interests have centered on non-probability sampling and weighting adjustments, mobile-first survey design, and data quality.
 
Randall K. Thomas, Chief Survey Methodologist & Senior Vice President
Randall is an internationally-recognized survey methodologist, responsible for overseeing the quality of research processes and projects for GfK Custom Research. He serves as a special consultant on projects requiring challenging multi-mode and custom panel designs. Trained in social psychology at Ohio State University, Randall has been one of the most prolific researchers on measurement using web-based surveys for the past 15 years and has more than 25 years of experience in experimental survey methodology across modes of interviewing and countries. His research interests focus on measurement of attitudes, intentions, and behaviors across devices and modalities.