How to perform ANOVA using the StatsModels library in python?
In this recipe, you will learn how to perform ANOVA using Python's StatsModels library
Recipe Objective - How to perform ANOVA using the StatsModels library in python?
Analysis of variance model includes anova_lm for ANOVA analysis using the linear OLS model and AnovaRM for ANOVA using iterative measurements within the ANOVA of the ANOVA.
For more related projects -
https://www.dezyre.com/projects/data-science-projects/deep-learning-projects
https://www.dezyre.com/projects/data-science-projects/neural-network-projects
Example:
# Importing libraries
import statsmodels.api as sm
from statsmodels.formula.api import ols
# Importing moore dataset from carData package
X = sm.datasets.get_rdataset("Moore", "carData").data
# Renaming column
X = X.rename(columns={"partner.status":"partner_status"})
# Fit and summarize ols model
model = ols('fscore ~ C(partner_status, Sum)*C(fcategory, Sum)',data=X).fit()
# type-1 anova summary
table_type_1 = sm.stats.anova_lm(model, typ=1)
# type-2 anova summary
table_type_2 = sm.stats.anova_lm(model, typ=2)
table_type_1
Output -
df sum_sq mean_sq F PR(>F)
C(partner_status, Sum) 1.0 7.932587 7.932587 0.231555 6.330623e-01
C(fcategory, Sum) 2.0 7561.365635 3780.682818 110.359336 8.768957e-17
C(partner_status, Sum):C(fcategory, Sum) 2.0 29.086807 14.543403 0.424527 6.570656e-01
Residual 39.0 1336.059416 34.257934 NaN NaN
table_type_2
Output -
sum_sq df F PR(>F)
C(partner_status, Sum) 67.253778 1.0 1.963159 1.690834e-01
C(fcategory, Sum) 7561.365635 2.0 110.359336 8.768957e-17
C(partner_status, Sum):C(fcategory, Sum) 29.086807 2.0 0.424527 6.570656e-01
Residual 1336.059416 39.0 NaN NaN
In this way, we can perform ANOVA using the StatsModels library in python.
What Users are saying..
Gautam Vermani
Having worked in the field of Data Science, I wanted to explore how I can implement projects in other domains, So I thought of connecting with ProjectPro. A project that helped me absorb this topic... Read More