Classification trees and linear regression analysis were used to build models to predict probabilities of infestation and amount of tree mortality in terms of basal area resulting from roundheaded pine beetle, Dendroctonus adjunctus Blandford, activity in ponderosa pine, Pinus ponderosa Laws., in the Sacramento Mountains, New Mexico. Classification trees were built for combined habitat types sampled and for each habitat type series or type sampled. Cross-validation estimates of classification accuracy ranged from 0.64 to 0.79. The data suggest that stands attacked by the roundheaded pine beetle exhibit poor growth during the last 5 years prior to attack, abundant host type, and smaller diameter than uninfested stands. Trees prone to attack by the roundheaded pine beetle within infested points also exhibited reduced growth rates and smaller diameters than uninfested trees. Linear regression analysis indicates that initial amount of ponderosa pine basal area is a good predictor variable for the amount of basal area affected.