Analyze Mayo Clinic Primary Biliary Cirrhosis, sequential data

 

Use the pbc dataset () to identify an important variable in a time to event context. 

First, assess the normality of each of the candidate variables and create a table showing the appropriate summary statistics ( e.g. mean +- sd or median)

Then, create a standard Cox regression model for survival using each of the variables. Then use LASSO regression to identify a parsimonious set of variables predictive of survival. Propose what you believe to be the best model for the prediction of survival.

Next, use an interesting R package you find online to identify any variables that may be non-linearly associated with the time to event outcome. 

Finally, create an interesting figure that you feel adequately displays and demonstrates the information that you have found.