The study demonstrates that more accurate profiles of prescription drug abusers can be created by separating age groups when determining the predictors of prescription drug abuse. Differences also showed up across age groups in how well other substance use predicts prescription drug abuse. The use of marijuana in the past year is an increasingly significant predictor of painkiller use for each successive older age group. Being married was associated with lower painkiller and stimulant use for 18- to 25-year-olds, but much higher stimulant use among 26- to 34-year-olds. In sum, the analysis suggests that more accurate profiles of prescription drug abusers can be obtained by either allowing coefficient estimates to vary by age or by estimating age-specific regression models. Further research was recommended. The nonmedical use of prescription drugs is a growing problem in the United States and worldwide. Previous studies that have identified the predictors of prescription drug abuse have either focused on a specific age group or pooled all age groups together into one sample, constraining the predictors to have the same effect across age groups. Using the 2001 to 2003 National Survey on Drug Use and Health, this study estimated separate models across five age groups for the past year nonmedical use of prescription drugs. Tables, note, and references