生存时间数据分析

用于分析可靠性和生存数据的非参数化方法和半参数化方法

生存分析是一种事件时间分析，即关注的结果是事件发生的时间。事件时间的示例有：健康科学研究的感染、疾病复发或恢复的时间；经济学研究的失业的持续时间；工程研究的机器零件失效前的时间或灯泡的寿命等。

要执行生存分析：

fitcox 函数提供一种面向对象的方法来拟合考克斯比例风险模型。生成的 CoxModel 对象包含许多统计量和分析方法。coxphfit 用于拟合考克斯模型的旧函数，它也支持代码生成。

函数

`ksdensity`	Kernel smoothing function estimate for univariate and bivariate data
`mle`	Maximum likelihood estimates
`mlecov`	Asymptotic covariance of maximum likelihood estimators
`evfit`	Extreme value parameter estimates
`expfit`	Exponential parameter estimates
`gamfit`	Gamma parameter estimates
`lognfit`	Lognormal parameter estimates
`normfit`	Normal parameter estimates
`wblfit`	Weibull parameter estimates
`fitdist`	对数据进行概率分布对象拟合
`distributionFitter`	打开分布拟合器

`ecdf`	Empirical cumulative distribution function
`ecdfhist`	Histogram based on empirical cumulative distribution function
`plotSurvival`	Plot survival function of Cox proportional hazards model (自 R2021a 起)
`probplot`	Probability plots
`wblplot`	Weibull probability plot

coxphfit Cox proportional hazards regression

fitcox Create Cox proportional hazards model (自 R2021a 起)

`coefci`	Confidence interval for Cox proportional hazards model coefficients (自 R2021a 起)
`discardResiduals`	Remove residuals from Cox model (自 R2022b 起)
`hazardratio`	Estimate Cox model hazard relative to baseline (自 R2021a 起)
`linhyptest`	Linear hypothesis tests on Cox model coefficients (自 R2021a 起)
`plotSurvival`	Plot survival function of Cox proportional hazards model (自 R2021a 起)
`survival`	Calculate survival of Cox proportional hazards model (自 R2021a 起)

CoxModel Cox proportional hazards model (自 R2021a 起)

What Is Survival Analysis?
Learn about censoring, survival data, and the survivor and hazard functions.
Survivor Functions for Two Groups
Find the empirical survivor functions and the parametric survivor functions using the Burr type XII distribution fit on data for two groups.
Hazard and Survivor Functions for Different Groups
Estimate and plot the cumulative hazard and survivor functions for different groups.
Kaplan-Meier Method
Estimate the empirical hazard, survivor, and cumulative distribution functions.
Cox Proportional Hazards Model
Adjust survival rate estimates to quantify the effect of predictor variables.
Cox Proportional Hazards Model Object
Create data for a Cox model with three stratification levels, then fit and analyze the resulting model.
Cox Proportional Hazards Model for Censored Data
Create a Cox proportional hazards model, and assess the significance of the predictor variables.
Cox Proportional Hazards Model with Time-Dependent Covariates
Convert survival data to counting process form, and then construct a Cox proportional hazards model with time-dependent covariates.
Analyzing Survival or Reliability Data
Analyze lifetime data with censoring by modeling the time to failure of a throttle from an automobile fuel injection system.