Background: Knowing which factors influence restoration longevity can help clinicians make sound treatment decisions. The authors analyzed data from The National Dental Practice-Based Research Network to identify predictors of early failures of amalgam and resinbased composite (RBC) restorations. Methods: In this prospective cohort study, the authors gathered information from clinicians and offices participating in the network. Clinicians completed a baseline data collection form at the time of restoration placement and annually thereafter. Data collected included patient factors, practice factors and dentist factors, and the authors analyzed them by using mixed-model logistic regression. Results: A total of 226 practitioners followed up 6,218 direct restorations in 3,855 patients; 386 restorations failed (6.2 percent) during the mean (standard deviation) follow-up of 23.7 (8.8) months. The number of tooth surfaces restored at baseline helped predict subsequent restoration failure; restorations with four or more restored surfaces were more than four times more likely to fail. Restorative material was not associated significantly with longevity; neither was tooth type. Older patient age was associated highly with failure (P <.001). The failure rate for children was 4 percent, compared with 10 percent for people 65 years or older. Dentist's sex and practice workload were associated significantly with restoration longevity. Conclusions: In this prospective cohort study, these factors were significantly predictive of failure for amalgam and RBC restorations: patient's age, a higher number of surfaces restored at baseline, the dentist's sex and the practice workload. Material choice was not significantly predictive in these early results. Practical Implications: If clinicians can recognize and identify the risk factors associated with early restoration failure, more effective treatment plans may be offered to the patient.