21

21.md

@@ -41,7 +41,7 @@ population['numbers'].hist(bins=100)
 # <matplotlib.axes._subplots.AxesSubplot at 0x112c72710> 
 ```
 
-![png](https://chrisalbon.com/statistics/frequentist/demonstrate_the_central_limit_theorem_5_1.png)
+![png](https://chrisalbon.com/statistics/frequentist/demonstrate_the_central_limit_theorem/demonstrate_the_central_limit_theorem_5_1.png)
 
 ```py
 # 查看数值的均值
@@ -65,7 +65,7 @@ pd.Series(sampled_means).hist(bins=100)
 # <matplotlib.axes._subplots.AxesSubplot at 0x11516e668> 
 ```
 
-![png](https://chrisalbon.com/statistics/frequentist/demonstrate_the_central_limit_theorem_11_1.png)
+![png](https://chrisalbon.com/statistics/frequentist/demonstrate_the_central_limit_theorem/demonstrate_the_central_limit_theorem_11_1.png)
 
 这是关键的图表，记住总体分布是均匀的，然而，这个分布接近正态。 这是中心极限理论的关键点，也是我们可以假设样本均值是无偏的原因。
 
@@ -177,7 +177,7 @@ plt.bar(list(probability_mass_function.keys()), probability_mass_function.values
 plt.show()
 ```
 
-![png](https://chrisalbon.com/statistics/frequentist/probability_mass_functions_10_0.png)
+![png](https://chrisalbon.com/statistics/frequentist/probability_mass_functions/probability_mass_functions_10_0.png)
 
 ## Spearman 排名相关度