Online Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 82 - Contributed Poster Presentations: Government Statistics Section
Type: Contributed
Date/Time: Monday, August 3, 2020 : 10:00 AM to 2:00 PM
Sponsor: Government Statistics Section
Abstract #313518
Title: A Novel Sampling Methodology for Risk Management Agency’s Improper Payment Rate Survey
Author(s): Franklin Duan* and Timothy Keller and Peter Quan
Companies: USDA NASS MD and University of Missouri-St. Louis and NASS, USDA
Keywords: Sampling Methodology; Improper Payment Rate ; stratification; Horvitz-Thompson
Abstract:

NASS develop a sampling methodology for Risk Management Agency’s (RMA) Improper Payment Survey for measuring the amount of improper payments in the Federal Crop Insurance Program (FCIP). The primary objective is to estimate the total amount of improper payments at the US level during a fiscal year to satisfy the Office of Management and Budget (OMB) precision standards. A secondary objective is to obtain estimates for the rate of improper payments at the level of an individual Approved Insurance Provider (AIP). Since the amount of total payments are known for every policy in the population, an estimate of the rate of improper payments is obtained by simply rescaling the estimate of total improper payments. The sample design has two levels of explicit stratification. The first level of stratification is defined by the AIP. Within each AIP, a second level of stratification is defined by the policies corresponding to the top, middle and bottom third of total payments for that AIP. The total amount of improper payments at the US level was obtained using the Horvitz-Thompson estimator.


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

Back to the full JSM 2020 program