Online Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 212 - GOVT CSpeed 1
Type: Contributed
Date/Time: Tuesday, August 10, 2021 : 1:30 PM to 3:20 PM
Sponsor: Government Statistics Section
Abstract #317888
Title: Application of Different Priors in Bayesian Logistic Regression Comparing Odds of Non-Response Among Strata in US Census of Horticulture Specialties in Two Selected States
Author(s): Bayazid Sarkar*
Companies: NASS/USDA
Keywords: Census of Horticulture Specialties; Bayesian Logistic Regression

The Census of Horticulture Specialties (COHS) is administered every five years to ascertain U.S. horticulture sector information. The COHS sampling frame comprises farms on NASS List Frame that have horticulture control data. The COHS sampling frame was stratified – within each state - using horticulture value of sales (VOS) as a measure of size. This presentation discusses using three different prior distributions (normal non-informative, normal informative and Cauchy) in a logistic regression model to determine whether the odds for California and Florida sampled elements of non-response is associated with strata.

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

Back to the full JSM 2021 program