# The Chi-squared Test >[!Question] Is the variation in your data just due to chance? Or does it have to do with one of the variables? >[!Abstract] The Chi-squared Test > Assess the **goodness of fit** > Calculated as follows: > $\chi^2 = \sum_i \frac{(O_i - E_i)^2}{E_i}$ > Where $O_i$ is the observed value of interest and $E_i$ is the expected value. > >**Used to check if two categorical variables are independent** ## Computation ### Chi-squared Test ```python from scipy.stats import chisquare chisquare(f_obs, ddof=1, f_exp=None, axis=1)>) ``` ### Testing for Independence ```python from scipy.stats import chi2_contingency tab_data = [[203, 150, 190, 305], [195, 170, 250, 400]] chi2_contingency(tab_data) ``` ## Use when - Testing the goodness of fit - To check if two categorical variables are independent