Introduction to Weighting with a focus on Nonresponse Adjustment - online
29/06/2023 - 30/06/2023
National Centre for Social Research (NatCen)
Dr. Pamela Campanelli
Intermediate (some prior knowledge)
This live online course covers why we need to deal with nonresponse bias in surveys and how weighting can be a good solution. The course explores the 3 levels of weighting: (1) correcting for unequal probabilities of selection in the sampling design, (2) adjusting for nonresponse and (3) calibrating to population totals. But the focus is on nonresponse adjustment. Learn about all the weighting methods that can be used and their pros and cons.
Participants should have knowledge about surveys. It is helpful for participants to be familiar with the statistical concepts of sampling variance, confidence intervals and regression analysis.
Run across two consecutive afternoons (29th and 30th June, 12:30 - 16:30) the course covers:
- Response rates versus nonresponse bias
- The nonresponse bias formula and its implications
- Study designs to find out who the nonrespondents are
- Correlates of nonresponse bias
- A short “refresher” of the statistical concepts used on the course.
- Background on weighting including the 3 standard steps of design weights, nonresponse weights and then calibration to population values.
(Each weighting method comes with examples and a discussion of the pros and cons of that method.)
- Design weights
- Basic weighting class adjustment for nonresponse
- Bulgarian weighting class example and combining weights
- 3 other things to keep in mind about weighting
- Re-scaling weights
- The effect of weighting
- Trimming (truncating) weights
- Other methods for nonresponse adjustment
- Propensity Score Weighting using logistic regression versus classification trees
- Four weighting examples
- British Household Panel Study (Nonresponse at household, individual and longitudinal levels)
- English Housing Survey (Address versus dwelling versus household)
- Weighting for “Push-to-Web” designs
- US Census Bureau Survey of Income and Program Participation
- What is calibration?
- And examples of raking and GREG
- Nonresponse handled as a separate stage or as part of calibration (with examples)
- Overall summary and software recommendations
The fee per teaching day is: £30 per day for students / £60 per day for staff working for academic institutions, Research Councils and other recognised research institutions, registered charity organisations and the public sector / £100 per day for all other participants. Fees include event materials. In the event of cancellation by the delegate a full refund of the course fee is available up to two weeks prior to the course. NO refunds are available after this date. If it is no longer possible to run a course due to circumstances beyond its control, NCRM reserves the right to cancel the course at its sole discretion at any time prior to the event. In this event every effort will be made to reschedule the course. If this is not possible or the new date is inconvenient a full refund of the course fee will be given. NCRM shall not be liable for any costs, losses or expenses that may be incurred as a result of the cancellation of a course, including but not limited to any travel or accommodation costs. The University of Southampton’s Online Store T&Cs also continue to apply
Website and registration:
Survey Research, Nonresponse , • Weighting • Calibration • Survey weighting • Response rates • Nonresponse Bias • Nonresponse Weights • Design Weights • Post-stratification • Propensity Score Weighting
Related publications and presentations: