Online Program Home
My Program

Abstract Details

Activity Number: 349
Type: Topic Contributed
Date/Time: Tuesday, August 2, 2016 : 10:30 AM to 12:20 PM
Sponsor: Survey Research Methods Section
Abstract #319997 View Presentation
Title: Modeling Survey Data with Regression Trees
Author(s): Daniell Toth*
Companies: Bureau of Labor Statistics
Keywords: Sample Design ; Establishment Surveys ; Interactions ; R Packages ; Recursive Partitioning

In this paper, we introduce the R package, RPMS, (Recursive Partitioning for Modeling Survey Data), which fits a linear model to survey data conditionally on variables selected through recursively partitioning. This application of recursive partitioning produces design consistent regression tree models of the data. We demonstrate the software through the modeling of establishment level employment data collected by the U.S. Bureau of Labor Statistics. These applications demonstrate the easily interpretable structure and the ability of regression trees to handle large data sets with complex associations among the variables.

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

Back to the full JSM 2016 program

Copyright © American Statistical Association