Abstract:
|
The USDA's National Agricultural Statistics Service (NASS) conducts a census of agriculture every 5 years, in years ending in 2 and 7. The census describes the characteristics of U.S. farms and the people who operate them. It is the only source of uniform, comprehensive data for every state and county. To adjust for undercoverage, nonresponse and misclassification, NASS adjusts the weights on the responding records using a capture-recapture methodology. However, the weights need to be further refined through a calibration process so that the census estimates agree with known population values. Some of the census estimates, such as demographic estimates, are included among the targets so that these estimates are not distorted during calibration. Current NASS calibration methodology is robust but often fails to match all target simultaneously. In this article, we describe a new calibration procedure based on L1-norm relative error. We present the results of a simulation study designed to investigate the consistency and efficiency of the estimators. The calibration estimator can match more targets simultaneously thus providing a foundation for a better methodology.
|