如何同时运行 5 个 OLS 回归并将结果输出到同一个表？

Question

我正在尝试创建一个表格，显示 5 个单独回归的系数和 p 值（具有显着性水平）。请参阅图片作为示例：

我运行了一系列代码，但总是得到 5 个单独的表。我无法提取 p 值和系数。

Answer 1

你可以这样做：

import numpy as np
import pandas as pd
import statsmodels.api as sm
from statsmodels.iolib.summary2 import summary_col

# Set seed for reproducible results
np.random.seed(0)

# Simulate toy data for the demonstration
n = 100  # number of observations
X1 = np.random.normal(0, 1, n) 
X2 = np.random.normal(0, 1, n) 
X3 = np.random.normal(0, 1, n)
X4 = np.random.normal(0, 1, n) 
X5 = np.random.normal(0, 1, n) 
Y = 2 + 1 * X1 + 2 * X2 + 3 * X3 - 1.5 * X4 + 0.5 * X5 + np.random.normal(0, 2, n)  # Dependent variable

df = pd.DataFrame({'X1': X1, 'X2': X2, 'X3': X3, 'X4': X4, 'X5': X5, 'Y': Y})


independent_vars = ['X1', 'X2', 'X3', 'X4', 'X5']

# Fit the models
models = []
for i in range(5):
    X = df[independent_vars[i]]  
    X = sm.add_constant(X)  
    model = sm.OLS(df['Y'], X).fit()
    models.append(model)

# Combine the results into a single table
results_table = summary_col(models,
                            stars=True,
                            model_names=[f'Model {i+1}' for i in range(5)],
                            info_dict={'R-squared': lambda x: f"{x.rsquared:.2f}",
                                       'No. observations': lambda x: f"{int(x.nobs)}"})

# Display the results table
print(results_table)

产生这个：

==================================================================
                  Model 1   Model 2   Model 3   Model 4   Model 5 
------------------------------------------------------------------
const            1.8433*** 1.7668*** 2.1342*** 1.8303*** 1.9413***
                 (0.4335)  (0.4085)  (0.3134)  (0.4644)  (0.4454) 
X1               1.4368***                                        
                 (0.4293)                                         
X2                         1.9801***                              
                           (0.3936)                               
X3                                   3.4614***                    
                                     (0.3286)                     
X4                                             -0.5027            
                                               (0.4889)           
X5                                                       0.9677** 
                                                         (0.4294) 
R-squared        0.1026    0.2053    0.5310    0.0107    0.0493   
R-squared Adj.   0.0934    0.1972    0.5262    0.0006    0.0396   
R-squared        0.10      0.21      0.53      0.01      0.05     
No. observations 100       100       100       100       100      
==================================================================
Standard errors in parentheses.
 * p<.1, ** p<.05, ***p<.01