Abstract
The objective of this study was to assess the effect of separating the functions of sampling for training and sampling for area estimation. Two classification and area estimation procedures were compared: 1) statistics developed on one segment were used to classify that segment, and 2) pooled statistics from the segments were used to classify a systematic sample of pixels in the stratum. Comparisons to USDA/ESCS estimates illustrate the potential of using a full-frame sampling approach. -from Authors
Original language | English (US) |
---|---|
Title of host publication | Purdue University, LARS Technical Report |
Volume | 062381 |
State | Published - 1981 |