|
Activity Number:
|
662
- State, County, and Local Government Statistics
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Thursday, August 3, 2017 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Government Statistics Section
|
|
Abstract #324341
|
View Presentation
|
|
Title:
|
Outlier Research in the Annual Survey of Local Government Finances
|
|
Author(s):
|
Peter Schilling* and Redouane Betrouni and Bac Tran
|
|
Companies:
|
US Census Bureau and US Census Bureau and US Census Bureau
|
|
Keywords:
|
robust estimation ;
small area ;
mixture models ;
outliers
|
|
Abstract:
|
The Annual Survey of Local Government Finances (ALFIN) is conducted by the U.S. Census Bureau and provides statistics about the financial activities of state and local governments across the nation. The Economic Directorate makes thousands of estimates at the state and local levels based on ALFIN, and uses small area methods due to low estimation cell sizes. The presence of outliers in ALFIN data is a concern due to violation of model-based assumptions. In this paper, we evaluate the use of transformations in the small area mixed models to handle outliers. Our research uses a Monte Carlo simulation experiment with data from census years 2007 and 2012 to conduct the evaluation.
|
Authors who are presenting talks have a * after their name.
