Extracting Regression Coefficients from statsmodels.api (original) (raw)

Last Updated : 23 Jul, 2025

data analysis and machine learning, regression analysis is a fundamental tool used to understand relationships between variables. Python's statsmodels library provides a powerful framework for performing regression analysis. This article delves into how to extract regression coefficients using statsmodels.api, focusing on practical implementation with technical insights.

Table of Content

Introduction to statsmodels

Statsmodels is a Python module that provides classes and functions for the estimation of many different statistical models, as well as for conducting statistical tests and data exploration. It is particularly useful for econometric and statistical analyses, providing a comprehensive suite of tools for linear regression, time series analysis, and more.

Once the model is fitted, we can extract the regression coefficients using below methods from the fitted model, which include the slope and intercept of the regression line u**sing the params Attribute. The params attribute of the fitted model object contains the coefficients.

Let's walk through a simple example of performing linear regression using statsmodels. First, prepare your data. For demonstration, let's create a synthetic dataset:

Python `

import numpy as np import pandas as pd

np.random.seed(0) X = np.random.rand(100, 1) y = 3 * X.squeeze() + 2 + np.random.randn(100) * 0.5

data = pd.DataFrame({'X': X.squeeze(), 'y': y})

`

**Building the Regression Model

To perform regression analysis, you need to define your dependent (endog) and independent (exog) variables. In this example, y is the dependent variable, and X is the independent variable.

Python `

import statsmodels.api as sm

Add a constant to the independent variable

X = sm.add_constant(data['X'])

Fit the Ordinary Least Squares (OLS) model

model = sm.OLS(data['y'], X) results = model.fit()

`

Once the model is fitted, you can extract the regression coefficients, which include the slope and intercept of the regression line.

Python `

Extract coefficients

coefficients = results.params print("Intercept:", coefficients['const']) print("Slope:", coefficients['X'])

Print the summary of the regression model

print(results.summary())

`

Output:

Intercept: 2.1110755387236146
Slope: 2.9684675107010206
OLS Regression Results

Dep. Variable: y R-squared: 0.747
Model: OLS Adj. R-squared: 0.744
Method: Least Squares F-statistic: 289.3
Date: Thu, 08 Aug 2024 Prob (F-statistic): 5.29e-31
Time: 13:16:46 Log-Likelihood: -72.200
No. Observations: 100 AIC: 148.4
Df Residuals: 98 BIC: 153.6
Df Model: 1
Covariance Type: nonrobust 

             coef    std err          t      P>|t|      [0.025      0.975]

const 2.1111 0.097 21.843 0.000 1.919 2.303
X 2.9685 0.175 17.009 0.000 2.622 3.315

Omnibus: 11.746 Durbin-Watson: 2.083
Prob(Omnibus): 0.003 Jarque-Bera (JB): 4.097
Skew: 0.138 Prob(JB): 0.129
Kurtosis: 2.047 Cond. No. 4.30

The params attribute returns a pandas.Series object, where each coefficient is indexed by the name of the corresponding variable. If you included a constant in your model using sm.add_constant(), the intercept will be labeled as 'const'.

For larger models, you might want to automate the extraction of coefficients into a more structured format, such as a DataFrame:

Python `

def get_coef_table(lin_reg): coef_df = pd.DataFrame({ 'coef': lin_reg.params.values, 'pvalue': lin_reg.pvalues.round(4), 'ci_lower': lin_reg.conf_int()[0], 'ci_upper': lin_reg.conf_int()[1] }, index=lin_reg.params.index) return coef_df

coef_table = get_coef_table(results) print(coef_table)

`

Output:

       coef  pvalue  ci_lower  ci_upper

const 2.111076 0.0 1.919284 2.302867
X 2.968468 0.0 2.622125 3.314810

**Conclusion

Extracting regression coefficients using statsmodels.api is a straightforward process that provides valuable insights into your data. By understanding the coefficients and their statistical significance, you can make informed decisions and predictions. This article covered the essentials of setting up a regression model, extracting coefficients, and interpreting the results. With these tools, you're well-equipped to perform robust regression analysis in Python.