| 我国农户入户调查数据预处理及在农户收入模型中的应用 |
| |
| 引用本文： | 曹昆,王成璋.我国农户入户调查数据预处理及在农户收入模型中的应用[J].世界科技研究与发展,2011,33(3):511-513. |
| |
| 作者姓名： | 曹昆 王成璋 |
| |
| 作者单位： | 西南交通大学经济管理学院,成都,610031 |
| |
| 摘 要： | 使用Grubbs检验法对直接入户采集获得的农村住户资料进行异常值检验，并对异常值进行删除，而后使用EM法对数据集由于无回答和异常值删除产生的缺失数据进行插补；并利用处理后的数据进行衣户收入关于其劳动力投入和资本投入的微观计量分析，得到结论：农户可用劳动力数量对农户收入影响最大，而农户家庭经营支出对农户收入的影响大于农户家庭生产性固定资产拥有量对农户收入的影响。
|
| 关 键 词： | 数据预处理 异常值检验 缺失值插补 农户收入 |
Application of Data Preprocessing for Rural Household Survey and Farmer's Income Model |
| |
| CAO Kun,WANG Chengzhang.Application of Data Preprocessing for Rural Household Survey and Farmer's Income Model[J].World Sci-tech R & D,2011,33(3):511-513. |
| |
| Authors: | CAO Kun WANG Chengzhang |
| |
| Institution: | (School of Economics ＆ Management, Southwest Jiaotong University, Chengdu 610031 ) |
| |
| Abstract: | Grubbs＇ test method is used to test the rural household survey data. Then EM algorithm is used to estimate the missing value. After that, a Farmer＇s income model is built to study the household income,which is effected by the input of household labor and capital. The results show that labor input is the most effective factor, while the operating expenditure of rural household is more effective than productive fixed assets. |
| |
| Keywords: | data preprocessing unusual values test missing value estimation farmer＇s income |
| 本文献已被 维普 万方数据 等数据库收录！ |
