Kew Gardens at Christmas
|
DeepStore
BNs encode conditional probability statements, where the arrows are missing
BNs can be used to forecast risk
We check the forecasts that flow from the model starting with the largest structure and moving on to the smallest elements of the structure.
Which model is the best fit overall?
Which of the individual nodes are poorly modelled?
What is the z-score for forecasts that flow from the model given the setting of the parent nodes?
bnmonitor vignette
Leonelli, M., Ramanathan, R., Wilkerson, R., & Leonelli, M. M. (2025). Package ‘bnmonitor’.
Leonelli, M., Ramanathan, R., & Wilkerson, R. L. (2023). Sensitivity and robustness analysis in Bayesian networks with the bnmonitor R package. Knowledge-Based Systems, 278, 110882.
Barons, M., Bhatia, S., Double, J., Fonseca, T., Green, A., Krol, S. & Underdown, D. H. (2021). Safeguarding the nation’s digital memory: towards a Bayesian model of digital preservation risk. Archives and Records, 42(1), 58-78.
Rachel_Wilkerson@baylor.edu Github @rachwhatsit