When Less is More: Historical Yield Data and Rating Area Crop Insurance Products

The Federal Crop Insurance Program -- operated by the United States Department of Agriculture's Risk Management Agency (RMA) -- offers various types of insurance, covers a multitude of crops, carries significant liability, and is the cornerstone of domestic farm policy. Currently, RMA uses county yield data from the 1950s onwards to set guarantees and estimate premium rates for their area yield and revenue insurance products but trims yield data prior to 1991 in rating their newer shallow loss products. The past 70 years reflect very significant innovations in both seed and farm management technologies; innovations that have likely moved mass all around the support of the yield distribution. Although the RMA rating methodology corrects for time-varying movements in the first two moments, it is unclear whether using the entire yield series remains appropriate. We use distributional tests and an out-of-sample retain-cede rating game to answer if RMA should or should not historically trim yields in estimating their premium rates. Despite small sample sizes and the need to estimate tail probabilities, the historical data appears to be sufficiently different such that trimming is justified. While we caution against extrapolation of our results, they do give cause for consideration in other empirical analyses using historical yield data.