The Barrier Island and Estuarine Wetland Physical Change Assessment was created to calibrate and test probability models of barrier island estuarine shoreline and sandline change for study areas in Virginia, Maryland, and New Jersey. The models examined the influence of hydrologic and physical variables related to long-term and event-driven (Hurricane Sandy) estuarine back-barrier shoreline and overwash (sandline) change. Input variables were constructed into a Bayesian Network (BN) using Netica. To evaluate the ability of the BN to reproduce the observations used to train the model, the skill, log likelihood ratio and probability predictions were utilized. These data are the probability and skill metrics for all four models: the long-term (LT) back-barrier shoreline change, event-driven (HS) back-barrier shoreline change, long-term (LT) sandline change, and event-driven (HS) sandline change.