Online Program Home
My Program

Abstract Details

Activity Number: 654 - Evaluating and Reducing Nonsampling Errors in Surveys
Type: Contributed
Date/Time: Thursday, August 1, 2019 : 10:30 AM to 12:20 PM
Sponsor: Government Statistics Section
Abstract #306691 Presentation
Title: Blasting Farmers with Email and Text Survey Notifications: Modeling Response Rate Effects
Author(s): Tyler Wilson* and Shane T. Ball and Benjamin Martin Reist
Companies: USDA, NASS and NASS and USDA, NASS
Keywords: Response rates; Establishment Survey; Logistic Regression; Survey Notifications; Survey Methods
Abstract:

Notifications of upcoming survey requests can increase participation. Technology has increased the way in which notifications can be given. Email and text notifications are two cost efficient options that organizations can use if contact requirements are met. Both are relatively unproven in their specific effects on increasing response rates.

The Crops Acreage and Production Survey (APS) is a quarterly survey measuring agriculture crop acreage, yields and production. To explore the effect of email and text survey notifications on response rates, two studies were conducted. During the June 2018 Crops APS quarter, email notifications were sent out to randomly assigned sample units (notification or control)—controlling for age, high-value producers, race, response history, regional location and sex. A similar study was conducted in September 2018 Crops APS, except telephone texts were sent instead of emails. Two logistic regression models were developed that reflect each study’s design. Results indicated that response rates were unaffected by either an email or text notification; however, several methodological issues were identified and are discussed.


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

Back to the full JSM 2019 program