An illustration of the use of the Difference-In-Differences regression model to estimate the effect of hurricanes on house prices

difference_in_differences_regression.py

import pandas as pd
from patsy import dmatrices
import statsmodels.api as sm


#Load the data set into a Pandas Dataframe
df = pd.read_csv('us_fred_coastal_us_states_avg_hpi_before_after_2005.csv', header=0)

#Print it
print(df)

#Form the regression expression in Patsy syntax. The intercept is assumed to be present and will be
# included in the data set automatically
reg_exp = 'HPI_CHG ~ Time_Period + Disaster_Affected + Time_Period*Disaster_Affected'

#Carve out the training matrices
y_train, X_train = dmatrices(reg_exp, df, return_type='dataframe')

#Build the DID model
did_model = sm.OLS(endog=y_train, exog=X_train)

#Train the model
did_model_results = did_model.fit()

#Print out the training results
did_model_results.summary()