Online Program Home
My Program

Abstract Details

Activity Number: 631 - Small Area Estimation: “Producing Estimates for Small Areas from Sampled Data”
Type: Invited
Date/Time: Thursday, August 1, 2019 : 10:30 AM to 12:20 PM
Sponsor: Survey Research Methods Section
Abstract #300458 Presentation
Title: Small Area Estimates Using Tree Based Models
Author(s): Daniell Toth* and Kelly McConville
Companies: U.S. Bureau of Labor Statistics and Reed College
Keywords: machine learning; random forest; sample design; indirect estimators; survey data; model-assisted

We investigate the use of models based on regression trees to produce estimates of population means for small areas. We discuss different types of domains and methods for handling them using a variety of tree based estimators and compare their performance using the US Bureau of Labor Statistics data.

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

Back to the full JSM 2019 program