LOSS highway segment mapping was developed from databases exported from DiExSys Vision Zero Suite model runs by highway Safety Performance Function (SPF) type. Data was linear referenced using CDOT's current LRS.

Prior to the preparation of statewide highway segnment LOSS mapping, safety performance of segments were corrected for the Regression to the Mean Bias (RTM). RTM phenomenon reflects the tendency for random events, such as vehicle crashes, to move toward the average during the course of an experiment or over time. For instance if a segment exhibits unusually high or unusually low crash frequency in a particular year, because of RTM we need to be aware that over the long run its true average is closer to the mean representing safety performance of similar facilities. The existence of the RTM bias has been long recognized and is now effectively addressed by using the Empirical Bayes (EB) method . The use of EB method is particularly effective when it takes a long time for a few accidents to occur, as is often the case on Colorado rural roads. The empirical Bayes (EB) method for the estimation of safety increases the precision of estimation and corrects for the regression to the mean bias. EB corrected values of frequency and severity of crashes were used in all SPF analysis to assess the magnitude of the safety problem.