Optimal Sample Design for Estimation of Catch from Electronically Reported Data

• Activity Number: 41 - Non-Probability Sample and Probability Sample Matters Under What Context?
• Type: Contributed
• Date/Time: Sunday, July 28, 2019 : 2:00 PM to 3:50 PM
• Sponsor: Survey Research Methods Section
• Author(s): Zhaoce Liu* and Lynne Stokes
• Companies: Southern Methodist University and Southern Methodist University
• Keywords: Optimal Sample Design; Non-probability Sample; Ecological Sampling; Recreational Fishing

Abstract

National Marine Fisheries Service (NMFS) collects data to estimate catch of recreational anglers. Currently, these data come from two surveys, a mail survey measuring effort (# of trips made in a given area) and an intercept survey measuring catch per unit effort (# of fish per trip by species). These data from are combined to provide an estimate of the total catch.

NMFS is experimenting with alternative data collection procedures that use self-reports anglers submit via electronic devices, such as cell phones. The objective is to improve the quality and speed of estimation, and/or to reduce cost. The self-reports are from a non-probability sample of anglers and may not be accurate. Thus its data are not used directly in estimation, but as auxiliary data to the sample of intercepts. The new estimator’s precision depends on several factors, including reporting rate, the accuracy of reported counts, and representativeness of the reporting sample, as well as the size of the dockside sample. This paper examines the tradeoff among these factors and provides a way to determine the optimal design for various implementations of the pilot survey.