Online Program

Return to main conference page

All Times ET

Program is Subject to Change

Wednesday, June 16
Wed, Jun 16, 1:30 PM - 3:30 PM
The Future of Establishment Surveys Is Easy as ABC: AI, Big Data, Cutting-Edge Survey Design

AI Models in Survey Estimation (307933)

*Kelly McConville, Reed College 
Daniell Toth, US Bureau of Labor Statistics 

Keywords: statistical learning, survey sampling, regression trees, penalized regression

In this talk, I will discuss the utility of machine learning models for increasing the efficiency of model-assisted estimators.  I will cover how to incorporate penalized splines, elastic net regression, regression trees, and random forests into the generalized regression estimator. Drawing on my collaborations with the U.S. Bureau of Labor Statistics and the U.S. Forest Service, we’ll see how these AI models can help us estimate the number of bartenders in the US and the average number of trees per acre in Daggett County, Utah.