Online Program Home
My Program

Abstract Details

Activity Number: 423 - Contributed Poster Presentations: Survey Research Methods Section
Type: Contributed
Date/Time: Tuesday, July 30, 2019 : 2:00 PM to 3:50 PM
Sponsor: Survey Research Methods Section
Abstract #304729
Title: Method for Selecting Calibration Weights in a Non-Probability Epidemiological Survey
Author(s): Joshua Curtis Black* and Karilynn Rockhill and Alyssa Forber and Elise Amioka and K. Patrick May
Companies: Rocky Mountain Poison and Drug Center and Rocky Mountain Poison and Drug Center and Rocky Mountain Poison and Drug Center and Rocky Mountain Poison and Drug Center and Rocky Mountain Poison and Drug Center
Keywords: drug abuse; non-probability; bias reduction; calibration
Abstract:

National probabilistic surveys on drug abuse are slow to change and final data are usually delayed by nearly two years. The Survey of Non-Medical Use of Prescription Drugs Program (NMURx) has developed a method for selecting weighting variables that improve estimates while retaining timely delivery of data. NMURx utilizes sampling from a panel company where participants are randomly selected from the panel pool, but individuals are self-selected into the panel. Raking was used to calculate weights based on eight potential variables. The absolute relative bias was calculated for 26 benchmarks. The average relative bias using unweighted data was 36.3%. Using geographic region, age, sex, smoking frequency, and limitation in activities produced the lowest average relative bias of 24.8%; this constituted a 31.5% reduction in relative bias. Use of all eight weighting variables was not as effective (average relative bias: 30.7%). Use of non-demographic weighting variables caused a substantial reduction in bias in a non-probability survey. Timely estimates can be produced with this method and be used as a first look into substance abuse before national probability based data are available.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2019 program