摘要(英) |
The Concordance index(C-index) was often used to measure the prediction accuracy of the model. This index can be used under uncensored and censored data. In the literature, we can use the parametric model or nonparametric method to obtain the C-index under the interval censored data. In this study, we would like to introduce the hazard regression models into the C-index to make the model prediction accuracy more efficient. The Cox model is used to incorporate into C-index due to its flexibility. Moreover, in case that proportional assumption fails, the accelerated failure time (AFT) model was used to replace the Cox model. The estimation of the semi-parametric model in interval censored data is not straighforward. Under the Cox model, we use the algorithm proposed by Anderson-Bergman (2015) to estimate the regression parameters in interval censored data. In addition, we use the method proposed by Gao, F., Zeng, D.,and Lin, D. Y. (2017) when AFT model is used. The performance of C-index is accessed by simulation study and the proposed method is applied to HIV data. |
參考文獻 |
[1]Anderson-Bergman, C. (2016). An efficient implementation of the EMICM algorithm for the interval censored NPMLE. Journal of Computational and Graphical Statistics. 81(15), 1-24.
[2]Anderson-Bergman, C. (2017). icenReg: Regression Models for Interval Censored Data in R. Journal of Computational and Graphical Statistics 81(12), 1-23.
[3]Gao, F., Zeng, D., and Lin, D. Y. (2017). Semiparametric Estimation of the Accelerated Failure Time Model with Partly Interval-Censored Data. Biometrics 73, 1161–1168.
[4]Goggins, W. B. and Finkelstein, D. M. (2000). A proportional hazards model for multivariate interval-censored failure time data. Biometrics 56, 940–943.
[5]Gonen, M. and Heller, G. (2005). Concordance probability and discriminatory power in proportional hazards regression. Biometrika 92, 965–970.
[6]Graf, E., Schmoor, C., Sauerbrei, W., and Schumacher, M. (1999). Assessment and comparison of prognostic classification schemes for survival data. Statistics in Medicine 18(17-18), 2529–2545.
[7]Harrell, F. E., Lee, K. L., and Mark, D. B. (1996). Multivariate prognostic models: Issues in developing models, evaluating assumptions and adequacy, and measuring and reducing errors. Statistics in Medicine 15, 361–387.
[8]Heagerty, P. J. and Zheng, Y. (2005). Survival model predictive accuracy and roc curves. Biometrics 61, 92-105.
[9]Huang, J., Wellner, J. (1997).Interval Censored Survival Data: A Review of Recent Progress.In Proceedings of the First Seattle Symposium in Biostatistics: Survival Analysis, 123–169. Springer-Verlag, New York.
[10]Liu, X., Jin, Z., and Graziano, J. H. (2012). Comparing paired biomarkers in predicting quantitative health outcome subject to random censoring. Statistical Methods in Medical Research 25, 447–457.
[11]Tsouprou, S. (2015). Measures of discrimination and predictive accuracy for interval censored survival data. Mathematical Institute Master Thesis, Leiden University Medical Center, Nederland. |