Survival AnalysisUniversity of Tennessee at Chattanooga生存分析-美国田纳西大学.docVIP

  • 4
  • 0
  • 约4.44万字
  • 约 51页
  • 2018-10-09 发布于重庆
  • 举报

Survival AnalysisUniversity of Tennessee at Chattanooga生存分析-美国田纳西大学.doc

Survival AnalysisUniversity of Tennessee at Chattanooga生存分析-美国田纳西大学

Survival Analysis – PAGE \* MERGEFORMAT 1 Printed on 10/9/2008 Survival Analysis Introduction (AKA Event History Analysis) Situation Analysis of data in which the dependent variable consists of two aspects – 1) whether or not the outcome occurred – a dichotomous characteristic and 2) the amount of time that elapsed before occurrence of the outcome – a quantitative characteristic. The typical situations with this type of dependent variable Medical literature Two treatments for a disease are given. We attempt to record 1) Whether or not each patient died – the dichotomous outcome – and 2) how long each patient survived until death – the continuous outcome. Group A given Drug A. Group B given Drug B. Are death rates different in the two groups? Are survival times different in the two groups? Turnover literature Persons are hired by an organization into two different buildings. We attempt to record 1) Whether or not each employee quits before retirement and 2) how long each employee is employed before quitting. Building A: Kill and Debone Building B: Cook Are turnover rates different in the two plants? Are there differences in length of service in the two plants? Two aspects of survival analysis: One Dichotomous and one Continuous Dichotomous: Dying / Leaving the company Continuous: Length of survival / Time at the company These two aspects – proportion dying/turning over and “average” time before death/turnover - are negatively correlated although not identical aspects of the response to treatment. If we could observed persons for an infinite period of time – until EVERYONE had died or quit, then we would probably just analyze the survival times – a positively skewed variable, but one for which there are plenty of analytic tools – Mann-Whitney, Kruskal-Wallis, transformations to normality, etc. The problem with this is that we don’t have an infinite period of time to wait until everyone quits or dies. Plus, it may be the case that we lose contact

文档评论(0)

1亿VIP精品文档

相关文档