Bayesian classification and regression trees for predicting incidence of cryptosporidiosis: confusion or loss matrix - classification of observed versus predicted presence and absences from the Bayesian CART model

Viewed: 1614

This dataset was gathered to predict the spatial distribution of the cryptosporidiosis infection using selected social-ecological factors and climate variables. Predictions were completed using a Bayesian CART (Classification and Regression Trees) model.

The dataset presents the confusion or loss matrix – classification of observed versus predicted presence (‘Yes’) and absences (‘No’) from the Bayesian CART model.

Location of data collection

kmlPolyCoords

153.552920,-9.929730 137.994575,-9.929730 137.994575,-29.178588 153.552920,-29.178588 153.552920,-9.929730

Publications

Hu, Wen, O'Leary, Rebecca, Mengersen, Kerrie, & Low-Choy, Sama (2011) Bayesian Classification and regression trees for predicting incidence of cryptosporidiosis. PLoS ONE, 6(8), pp. 1-8. http://eprints.qut.edu.au/52459/

Research areas

Infectious diseases

Classification

Spatial distribution

Cryptosporidium

Decision trees

Bayes theorem

Bayesian

Absences

Observed

Probability distribution

Cryptosporidiosis

Matrix

Cite this collection

Hu, Wenbiao; O'Leary, Rebecca A.; Mengersen, Kerrie; Choy, Samantha Low (2013): Confusion or loss matrix – classification of observed versus predicted presence (‘Yes’) and absences (‘No’) from Bayesian CART model. Table_1.xls. PLOS ONE.