+ Reply to Thread
Results 1 to 4 of 4

Thread: Survival analysis

  1. #1
    Points: 883, Level: 15
    Level completed: 83%, Points required for next Level: 17

    Thanked 0 Times in 0 Posts

    Survival analysis

    I know this forum is probably not the right place to post my question, but considering the impressive help I have obtained hare and the (unimpressive nonexisting) responce from other sites and some biostatistician, I decided to post my question here (appology to the admin, and i hope you allow this question to remain here).
    Here is the problem
    I am trying to study the effect of the timing of introducing a certain drug on the risk of developing a side effect (bleeding). The theory is that delaying drug indroduction will reduce the risk of side effect:
    I have two groups:
    1- Group 1: the reference group: A number of patients that I follow for a period of time to see if they develope a bleeding, this is the group that helps me to understand the bakground risk of bleeding in the refernce population

    2- Group 2: containing patients who started the drug at different points of time after inclusion in the study, so some where followed for 2 weeks before starting the drug and continued to be followed up, some started at 4 weeks and continued to be followed up after starting the drug to see their risk of developing bleeding
    so I am trying to find the time interval of drug introduction which results in the lowest risk of bleeding compared to the background population.
    I understand this is a survival analysis of course, but could anyone please please try to help me on how to do this? maybe refer me to an article or suggest an analysis?
    THank you in advance

  2. #2
    Fortran must die
    Points: 58,790, Level: 100
    Level completed: 0%, Points required for next Level: 0
    noetsi's Avatar
    Thanked 915 Times in 874 Posts

    Re: Survival analysis

    I am not sure what you mean by survival analysis. Commonly that is used to mean Cox Proportional Hazard where you are estimating the probability of leaving in a given interval having not left to that interval I believe (or of surviving to a certain interval). It deals with censored data a major issue (that is data you do not directly observe such as individuals who leave after the study is over or before it begins).

    I don't think that is what you mean by survival analysis however although I would think you could apply delays of treatment as a predictor of leaving the system (dying). I would guess your issue is handled most often with ANOVA of some sort, probably a repeated measure design but I know too little about that to advice.

    I don't see any problem with this thread being here, you might not find someone who is an expert in this issue.
    "Very few theories have been abandoned because they were found to be invalid on the basis of empirical evidence...." Spanos, 1995

  3. #3
    Omega Contributor
    Points: 38,303, Level: 100
    Level completed: 0%, Points required for next Level: 0
    hlsmith's Avatar
    Not Ames, IA
    Thanked 1,185 Times in 1,146 Posts

    Re: Survival analysis

    Yeah on the surface this is a confusing model because what do you put for time to initiation for nontreatment variable. Not sure, perhaps run it without the nontreatment group for fun.

    You are predicting GI bleed correct?

  4. #4
    TS Contributor
    Points: 14,811, Level: 78
    Level completed: 91%, Points required for next Level: 39
    Miner's Avatar
    Greater Milwaukee area
    Thanked 405 Times in 363 Posts

    Re: Survival analysis

    This sound like arbitrary censoring. Unlike a typical survival analysis where there is a simultaneous start and everything is right censored, arbitrary censoring allows staggered start times.

+ Reply to Thread


Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts

Advertise on Talk Stats