Pure Premium Regression with the Tweedie Model
By Glenn Meyers
Fitting regression models to insurance loss data has always been problematic. The problem is particularly acute for data from individual insurance policies where most of the losses are zero, and for those policies with a positive loss, the losses are highly skewed. Most of the traditional regression models do not deal with a mixture of discrete losses of zero and continuous positive losses. One way of dealing with this problem is to fit separate models to the frequency and severity, and estimate the pure premium by multiplying the result of each model. One can take issue with assumption of “separate” models.
To view Download Remainder of Article click here