Skip to content

Commit 3711d81

Browse files
committed
up panel data models
1 parent 7dd088c commit 3711d81

158 files changed

Lines changed: 125870 additions & 2959 deletions

File tree

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

Lecture/00_intro.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -141,7 +141,7 @@
141141
### 非参数估计方法
142142

143143
- Wasserman (2006)《All of Nonparametric Statistics》, [PDF](https://www.stat.cmu.edu/~brian/valerie/617-2022/0%20-%20books/2006%20-%20Wasserman%20All%20Of%20Nonparametric%20Statistics.pdf)
144-
144+
- ———. 2006. All of Nonparametric Statistics. Springer Texts in Statistics. New York: Springer. https://doi.org/10.1007/0-387-30623-4.
145145

146146
### 其它
147147

Lecture/basic_distribution/02_stats_overview.md

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -102,6 +102,8 @@ $$
102102
然而,即使是随机抽样,也常常是**有条件的**。例如:
103103

104104
- **分层抽样**:先将总体按某个变量(如行业、地区、规模)分组,再在每组内进行随机抽样。CHFS 的调查设计就采用了分层多阶段抽样。
105+
- 适用场景:当总体具有明显的异质性时 (比如,不同行业的企业规模差异较大),分层抽样可以确保样本在关键特征上与总体保持一致,控制混杂变量。
106+
- **系统抽样**:按照一定的间隔(如每隔10个企业抽取一个)进行抽样。这种方法简单易行,但需要确保总体没有周期性结构,否则可能引入偏差。
105107
- **聚类抽样**:先随机抽取若干"群组"(如省份、社区),再对选中的群组进行全面调查或进一步抽样。
106108

107109
这意味着,即使在随机抽样的框架下,我们也需要理解**条件分布**(Conditional Distribution)的概念——我们观察到的数据,往往是在特定条件下产生的。

Lecture/causal_intro/05_causal_ols.ipynb

Lines changed: 225 additions & 84 deletions
Large diffs are not rendered by default.
90.5 KB
Loading
292 KB
Loading
Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,6 @@
1+
2+
3+
![fig1_normalized_close](https://fig-lianxh.oss-cn-shenzhen.aliyuncs.com/fig1_normalized_close.png){width="90%"}
4+
5+
6+
![20260408112943](https://fig-lianxh.oss-cn-shenzhen.aliyuncs.com/20260408112943.png)

0 commit comments

Comments
 (0)