| Sign In to gain access to subscriptions and/or personal tools. |
Kaplan-Meier Analysis of Dental Implant Survival: A Strategy for Estimating Survival with Clustered Observations'Department of Oral Health Policy and Epidemiology, Harvard School of Dental Medicine, 188 Longwood Avenue, Boston, MA 02115, schuang{at}hsph.harvard.edu
Department of Biostatistics, Harvard School of Public Health, 677 Huntington Avenue, Boston, MA 02115
Department of Biostatistics, Harvard School of Public Health, 677 Huntington Avenue, Boston, MA 02115
Department of Oral and Maxillofacial Surgery; Harvard School of Dental Medicine and Massachusetts General Hospital, 55 Fruit Street, Warren 1201, Boston, MA 02114 The study's purposes were to estimate dental implant survival in a statistically valid manner and to compare three models for estimating survival. We estimated survival using three different statistical models: (1) randomly selecting one implant per patient; (2) utilizing all implants, assuming independence among implants from the same subject; and (3) utilizing all implants, assuming dependence among implants from the same subject. The cohort was composed of 660 patients who had 2286 implants placed. Due to the high success rates of implants, the five-year survival point and standard error estimates varied little among the three models. Patients at high risk for implant failure (smokers) manifested greater variation in the standard error estimates among the three models, 8.2%, 4.0%, and 5.6%, respectively. To obtain statistically valid survival confidence intervals when performing Kaplan-Meier survival analyses, we recommend adjusting for dependence when there are multiple observations within the same subject.
Key Words: dental implant survival analysis Kaplan-Meier Estimator consistency asymptotic variance dependency correlation
Journal of Dental Research, Vol. 80, No. 11,
2016-2020 (2001) This article has been cited by other articles:
|
|
|||||||||||||||||||||||||||||||||||||||


