+ Reply to Thread
Results 1 to 2 of 2

Thread: Empirical Survivor Function (esf)

  1. #1
    Points: 5,695, Level: 48
    Level completed: 73%, Points required for next Level: 55

    Posts
    79
    Thanks
    31
    Thanked 2 Times in 2 Posts

    Empirical Survivor Function (esf)




    From page 26, chapter 2 of the reference "Tableman, M., & Kim, J. S. (2003). Survival analysis using S: analysis of time-to-event data. CRC press", I have found the definition of the empirical survivor function (esf) is

    S(t) = (number of individuals > t)/n .

    But from page 80, chapter 3 of the reference "Lawless, J. F. (2011). Statistical models and methods for lifetime data (Vol. 362). John Wiley & Sons",

    esf, S(t) = (number of individuals >= t)/n .

    Which formula is correct?

    Consider a lifetime data:

    t = 9 13 13 18 33 28 31 34

    By the definition of esf from the first reference, S(18)= 4/8=0.5.

    By the definition of esf from the second reference, S(18)= 5/8=0.625.

    Which one is conventional?

    Thanks for your attention.

  2. #2
    TS Contributor
    Points: 12,501, Level: 73
    Level completed: 13%, Points required for next Level: 349
    rogojel's Avatar
    Location
    I work in Europe, live in Hungary
    Posts
    1,491
    Thanks
    162
    Thanked 334 Times in 314 Posts

    Re: Empirical Survivor Function (esf)


    hi,
    consider that at S(19) both definitions have the same value . As in general the value at a given point is much less important then the general shape of the function, I would say that both definitions are ok as long as used consistently.

  3. The Following User Says Thank You to rogojel For This Useful Post:

    Cynderella (11-05-2017)

+ Reply to Thread

           




Tags for this 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