Online Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 352 - Small Area Estimation, Analysis of Complex Sample Survey Data, and New Advances for Health Surveys
Type: Contributed
Date/Time: Thursday, August 12, 2021 : 10:00 AM to 11:50 AM
Sponsor: Survey Research Methods Section
Abstract #317837
Title: Constructing UpSet Plot for Survey Data with Weights Using SAS Survey Package and R UpSetR Package
Author(s): Julia Soulakova* and Camilo Gomez and Alexander Goponenko
Companies: College of Medicine at Universtity of Central Florida and Graduate Student, UCF and Graduate Student, UCF
Keywords: multi-stage sampling; exploratory analysis; data visualization; software development
Abstract:

The UpSet plot is a convenient tool to demonstrate frequencies and percentages for intersection of multiple sets, e.g., the percentage of e-cigarette users who choose e-cigarettes over the regular cigarettes due to all these reasons: (1) e-cigarettes can be used in places where smoking is banned, (2) use of e-cigarettes is less harmful to user’s health and (3) health of people around, and (4) e-cigarettes aid in smoking cessation among dual users (users of e- and regular cigarettes). The UpSet plot can be conveniently constructed in R but is not suitable for survey data collected via complex sampling. We illustrate how one can construct the UpSet plots of weighted frequencies and relative weighted frequencies (percentages) using SAS® Survey Package and R UpSetR Package. To illustrate the approach, we constructed the plots for perceived reasons for e-cigarette use (stated above). The data source was the Tobacco Use Supplement to the Current Population Survey. The UpSet plots illustrated that among different combination of reasons for e-cigarette use, most commonly, e-cigarette users reported all four reasons simultaneously (35%), followed by reasons 2, 3 and 4 simultaneously (23%).


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

Back to the full JSM 2021 program