中国居民收入调查（CHIP）2018 年波次数据，由北京师范大学中国收入分配研究院主持。覆盖城镇住户、农村住户、流动人口三个分样本，是中国收入分配 / 不平等 / 贫困 研究的核心数据集。
China Household Income Project 2018 registers 17 variables — 4 commonly used as dependent variables, 6 as core regressors and 11 as controls. Common research directions for this dataset include: 收入不平等的代际传递, 城乡 / 户籍收入差距分解.
收入不平等的代际传递: DV ind_income, IV edu_years, controls gender, age, hukou.
城乡 / 户籍收入差距分解: DV ind_income, IV hukou, samp_type, controls age, edu_years, occupation.
| name | label | type/role | data file | description · keywords |
|---|---|---|---|---|
| pid | 个人ID Person ID | identifier / identifier | person | 个人唯一标识符 个人编号 |
| hid | 家庭ID Household ID | identifier / identifier | person | 家庭唯一标识符 家庭编号 |
| samp_type | 样本类型 Sample type | categorical / control | person | 三个分样本之一 样本类型城镇农村流动 |
| gender | 性别 Gender | binary / control | person | 受访者性别 性别 |
| age | 年龄 Age | continuous / control | person | 受访者年龄 年龄 |
| education | 受教育程度 Education attainment | ordinal / iv,control | person | 最高学历分类 教育学历受教育 |
| edu_years | 受教育年限 Years of schooling | continuous / iv,control | person | 完成教育累计年限 教育年限受教育年限 |
| hukou | 户口性质 Hukou status | binary / iv,control | person | 户口类型 户口户籍农业户口非农 |
| ind_income | 个人年总收入 Individual annual total income | continuous / dv,iv | person | 个人来自所有来源的年度税前总收入 收入个人收入总收入 |
| wage_income | 工资性收入 Wage income | continuous / dv | person | 受雇/被雇佣的劳动报酬 工资工资收入 |
| transfer_income | 转移性收入 Transfer income | continuous / control | person | 退休金、低保、失业金等转移支付 转移收入养老金社保 |
| occupation | 职业类型 Occupation | categorical / control | person | 国家标准职业分类大类 职业工种 |
| marital | 婚姻状况 Marital status | categorical / control | person | 婚姻状况 婚姻 |
| hh_income | 家庭年总收入 Household annual total income | continuous / dv,iv | household | 家庭年度总收入 家庭收入家庭总收入 |
| hh_income_pc | 家庭人均年收入 Per-capita household income | continuous / dv,iv | household | 家庭年总收入除以家庭人口 人均收入家庭人均 |
| hh_size | 家庭规模 Household size | continuous / control | household | 家庭常住人口数 家庭规模家庭人数 |
| province | 省份 Province | categorical / control | household | 调查省份代码 省份地区 |
The codebook is an open lookup. The Wizard consumes the same codebook to drive code generation — upload your data and the system auto-recognises variables, applies cleaning rules, recommends research designs, runs regressions and produces a Word report.