In order to investigate the general reliability assessment methods based on performance degradation data,two commonly used stochastic process approaches,bilinear process method and random-effect model were studied.Ana...In order to investigate the general reliability assessment methods based on performance degradation data,two commonly used stochastic process approaches,bilinear process method and random-effect model were studied.Analyzing procedure and effectiveness of these two methodologies were studied and compared.Meanwhile,the two approaches were illustrated through practical applications.The residual plots and the 10th percentile curves of the two methods were presented to demonstrate the comparative results.The randomeffect model yielded more volatile residuals and a lower and unsafe 10th percentile curve.Consequently the bilinear process model can be concluded to derive more reasonable results due to its one-stage estimation property.展开更多
基金National Natural Science Foundation of China(11202011)Beijing Natural Science Foundation(3154034)+1 种基金Fundamental Research Funds for the Central Universities(YWK13HK11)National Basic Research Program of China(2012CB720000)
文摘In order to investigate the general reliability assessment methods based on performance degradation data,two commonly used stochastic process approaches,bilinear process method and random-effect model were studied.Analyzing procedure and effectiveness of these two methodologies were studied and compared.Meanwhile,the two approaches were illustrated through practical applications.The residual plots and the 10th percentile curves of the two methods were presented to demonstrate the comparative results.The randomeffect model yielded more volatile residuals and a lower and unsafe 10th percentile curve.Consequently the bilinear process model can be concluded to derive more reasonable results due to its one-stage estimation property.
文摘目的将共享随机效应模型(shared random-effect model,SREM)应用于轻度认知障碍(mild cognitive impairment,MCI)向认知正常(normal cognition,NC)逆转的研究,比较不同纵向认知标志物对MCI逆转的预测性能,并评价影响因素的协变量效应。方法SREM模型包括两个子模型,其中纵向子模型采用线性混合效应模型对纵向认知标志物的变化轨迹建模,生存子模型采用比例风险模型对生存过程建模。基于对数似然函数值和信息准则进行模型拟合优度检验,采用ROC曲线下面积(area under the curve,AUC)评价不同纵向认知标志物(MMSE、CDRSB、FAQ、ADAS11、ADAS13和ADASQ4)对MCI逆转的预测性能;同时进行纵向子模型和生存子模型的影响因素分析。结果843名MCI患者中72名(8.54%)在随访结束后逆转为NC。以spline-PH-GH参数分布为基准风险函数的SREM模型对数似然函数值最大,AIC和BIC最小;以CDRSB为纵向认知标志物建立的SREM模型拟合最好,在不同时间的AUC值均表现良好,范围为0.797~0.852,且预测误差最小,范围为0.0427~0.0429;年龄、性别、受教育程度、婚姻状况和APOEε4基因均会影响MCI患者的认知功能和日常活动功能,六种纵向认知标志物均会影响MCI患者的逆转。结论CDR评分对MCI患者的认知功能和逆转预测性能最佳;认知功能和日常活动功能可作为MCI逆转的动态监测指标。
