Post stratification assessment of the NASS automated stratification method based on the Cropland Data Layer

Abstract

Area Sampling Frames (ASFs) are the foundation of the agricultural statistics program of USDA National Agricultural Statistics Service (NASS). A geospatial Cropland Data Layer (CDL) based automated stratification (AS) method was recently implemented to achieve higher accuracies than traditional stratification (TS), based on visual interpretation, in cultivated areas. This paper extends the AS assessment to the post stratification estimates. South Dakota (SD) US 2013 post stratification estimates, based on AS, are compared with the SD 2013 June Agricultural Survey estimates based on TS. Post stratification estimates obtained using AS are comparable, to the TS estimates, based on estimate percent differences. Considering the significant improvement in accuracy using AS in cultivated strata in five test states, improved accuracy in the highly cultivated stratum and improved stratum homogeneity in this study, it is concluded that the CDL based AS method generates ASFs that are more objective, efficient, accurate, and homogeneous and reduces labor costs.