Get startedGet started for free

Congratulations!

1. Congratulations!

Well done! You have reached the final video of Survival Analysis in Python. Let's recap what we've learned.

2. Why survival analysis?

We learned that survival analysis is a set of statistical methods we use for time-to-event data and censoring is the main reason why we cannot use traditional methods such as linear regression.

3. Estimate survival curves

We learned to analyze time-to-event data using its survival curve, which gives us the probability of survival at any given time. We learned about non-parametric estimators like the Kaplan-Meier estimator and parametric ones like the Weibull estimator.

4. The lifelines package

We learned about the lifelines package and steps to fit a survival curve.

5. Survival curve with covariates

We also learned that we could analyze the effects of different factors on survival. We could use the log-rank test to compare survival functions of groups and determine if they are different. The Weibull model and Cox proportional-hazards model help us quantify the impact of each factor and make predictions with new data. Now you have the tools you need to more accurately analyze and predict survival data such as machine failure times, user conversion and churn, and how long it takes patients to recover from illnesses.

6. Thank you!

Thank you!