농업관측 품목별 표본농가 재설계 연구

Abstract

The purpose of this research is to provide the sample design for estimating the amount of production and production activities of agricultural sectors (vegetables, fruits, vegetable fruits, livestock, grain). The sample design is based on 2005 agricultural census data and other related government data. Two stage stratified random sampling is applied for the sample design, where the first stratum is a sixteen geographical area (province), and the second stage is a stratum within province. Before computing sample size we cut off small farms from the population. The contribution from this part of the population is extremely small in comparison with the remaining population. It may be tempting not to use resources on farms that contribute little to the overall result of the survey. Moreover, this reduces the response burden for these small farms. The sampling frames are determined from the target population after subtracting farms that represent the bottom parts of the total cultivating area for each item. These farms were excluded from the frame so that the sample size could be reduced without significantly affecting quality. And then, the values of the sample sizes in the respective strata are chosen by Neyman allocation. A total of 17,989 sample agricultural households for 55 items - 7,252, 3,678, 2,148, 2,398 and 2,726 samples for the vegetables, fruits, vegetable fruits, livestock and grain respectively - are selected. In each stratum the sample households are systematically selected. The sample is self-weighted in each stratum while sampling rates are different from stratum to stratum.