Utilization of Cluster Analysis on the Sampling Selection of the Model-based Sampling Survey
碩士 === 國立成功大學 === 統計學系 === 104 === For the prediction problem in survey sampling under a finite population, n sampling units are selected out of N population units and observed to predict the population quantity of interest. The optimal sampling strategies proposed by different authors in the past c...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | zh-TW |
| Published: |
2016
|
| Online Access: | http://ndltd.ncl.edu.tw/handle/4r7c49 |
| Summary: | 碩士 === 國立成功大學 === 統計學系 === 104 === For the prediction problem in survey sampling under a finite population, n sampling units are selected out of N population units and observed to predict the population quantity of interest. The optimal sampling strategies proposed by different authors in the past can be used to select the optimal sample with which the mean-square error can be minimized. However, the computational load can be very extensive, and the optimization algorithm is not easy to implement. Additionally, the exact population distribution has to be assumed.
Two model-based sampling selection methods based on Cluster Analysis under a given sample size n are proposed in this article. Both design are better than SRSWOR in terms of given lower prediction mean-square error. These sampling methods do not require extensive computation nor exact population distribution to select the sampling units. Simulation study shows that they can be more effective than SRSWOR. An example on the utilization of the proposed sampling methods in practice is also presented.
|
|---|