Adjusting for Misclassification: A Three-Phase Sampling Approach

TL;DR

This paper introduces a three-phase sampling method to correct misclassification bias in agricultural surveys, improving the accuracy of US farm estimates by adjusting for non-response and classification errors.

Contribution

It develops a novel three-phase survey estimator and variance formula to address misclassification and non-response in agricultural data collection.

Findings

Provides a design-unbiased variance estimator.

Demonstrates improved farm estimate accuracy.

Addresses misclassification in survey data.

Abstract

The United States Department of Agriculture's National Agricultural Statistics Service (NASS) conducts the June Agricultural Survey (JAS) annually. Substantial misclassification occurs during the pre-screening process and from field-estimating farm status for non-response and inaccessible records, resulting in a biased estimate of the number of US farms from the JAS. Here the Annual Land Utilization Survey (ALUS) is proposed as a follow-on survey to the JAS to adjust the estimates of the number of US farms and other important variables. A three-phase survey design-based estimator is developed for the JAS-ALUS with non-response adjustment for the second phase (ALUS). A design-unbiased estimator of the variance is provided in explicit form.