The document contains questions and complete standard solutions to the Compulsory assignment in BAN404 at NHH.
In the tasks, the dataset dataOhlsson in the R-package insuranceData shall be analyzed, first in a regression framework and then in a classification framework. Use help(dataOhlsson) to read about the dataset but note that the variable kon is gender and not age as said in the help-function. In both tasks you should split the data into training and test datasets and use the them in

The document contains questions and complete standard solutions to the Compulsory assignment in BAN404 at NHH.
In the tasks, the dataset dataOhlsson in the R-package insuranceData shall be analyzed, first in a regression framework and then in a classification framework. Use help(dataOhlsson) to read about the dataset but note that the variable kon is gender and not age as said in the help-function. In both tasks you should split the data into training and test datasets and use the them in an appropriate way.
1. Regression
a) Use descriptive statistics and graphical tools (plots) to summarize the claim cost skadkost. Also,investigate the relationship between skadkost and antskad. Interpret the results.