摘要(英) |
The most commonly used model for survival analysis is the multiplicative effect model, such as Cox proportional hazard model, accelerated failure time model. However, the covariates of some biomedical data are more appropriately described by additive effects, such as the Aalen additive model.In complicated data sets some of the covariates maybe suitable for multiplicative effects,
and others maybe suitable for additive effects. In this case, a more generalized additive-multiplicative model maybe appropriate for this kind of data. In this study, we propose an additive-multiplicative model to analyze data, and with the baseline hazards function based on Weibull, loglogitic and lognormal distribution.
In addition, the longitudinal covariates are described by the mix-effects model, and the parameters are estimated through the joint likelihood function using EM algorithm. The multiplicative model and additive model are the special case of the additive-multiplicative model, we may use the likelihood ratio test to do the model selection. The simulation study is used to evaluate the proposed
approach, which is applied to the data of Taiwanese HIV/AIDS cohort study to verify its usefulness. |
參考文獻 |
翁瑄佑. 台灣愛滋病實例研究-以聯合模型探討cd4 細胞數以及病毒乘載
量對愛滋病患存活時間之關係; an aids case study in taiwan-the relationship
between the survival time of aids patients and their cd4 counts and viral load
using joint model to explore. Master’s thesis, 國立中央大學, 2013.
林家聿. 台灣愛滋病實例研究-以聯合模型探討愛滋病患存活時間與
相關生物指標之關係; an aids case study in taiwan-using joint model to
explore the relationship between the survival time of aids patients and related
biomarkers. Master’s thesis, 國立中央大學, 2016.
徐永東. 加乘法風險模型結合長期追蹤資料之聯合模型; joint modeling of
additive-multiplicative hazard model and longitudinal data. Master’s thesis,
國立中央大學, 2016.
王畯嶸. Joint modeling of parametric additive-multiplicative hazards model
and longitudinal data. Master’s thesis, 國立中央大學, 2017.
Aalen, O. A model for nonparametric regression analysis of counting processes.
In Mathematical Statistics and Probability Theory (New York, NY, 1980),
W. Klonecki, A. Kozek, and J. Rosi?ski, Eds., Springer New York, pp. 1–25.
Booth, J. G., and Hobert, J. P. Maximizing generalized linear mixed model
likelihoods with an automated monte carlo em algorithm. Journal of the Royal
Statistical Society: Series B (Statistical Methodology), 61 (1999), 265–285.
Cox, D. R. Partial likelihood. Biometrika, 62 (1975), 269–276.
Dempster, A. P., Laird, N. M., and Rubin, D. B. Maximum likelihood from
incomplete data via the em algorithm. Journal of the royal statistical society.
Series B (methodological) (1977), 1–38.
Henderson, R., Diggle, P., and Dobson, A. Joint modelling of longitudinal measurements
and event time data. Biostatistics, 1 (2000), 465–480.
Lin, D. Y., and Ying, Z. Semiparametric analysis of general additivemultiplicative
hazard models for counting processes. The Annals of Statistics,
23 (1995), 1712–1734.
Murphy, S. A., and Sen, P. K. Time-dependent coefficients in a cox-type regression
model. Stochastic Processes and their Applications 39 (1991), 153–180.
Scheike, T. H., and Zhang, M. J. An additive–multiplicative cox–aalen regression
model. Scandinavian Journal of Statistics, 29 (2002), 75–88.
Tseng, Y. K., Hsieh, F., and Wang, J. L. Joint modelling of accelerated failure
time and longitudinal data. Biometrika, 92 (2005), 587–603.
Wulfsohn, M. S., and Tsiatis, A. A. A joint model for survival and longitudinal
data measured with error. Biometrics, 53 (1997), 330–339. |