Online Program

A Problem in Small Area Estimation: Cash Rental Rates

Keywords: mixed models, small area estimation, empirical bayes, hierarchical bayes

The USDA National Agricultural Statistics Service (NASS) conducts an annual Cash Rents survey to estimate county level cash rental rates for three land use categories (non-irrigated cropland, irrigated cropland, and pasture). This information is used by economists, farmers, and government agencies. A major issue is that survey indications for counties are unstable due to small realized sample sizes. We investigate the use of mixed models to obtain reliable estimates of average cash rental rates at the county level. Small area estimation techniques such as empirical Bayes and hierarchical Bayes are examined.