Survival Analysis Notes

Survival Analysis Notes - Notes on Survival analysis...

Info icon This preview shows pages 1–5. Sign up to view the full content.

View Full Document Right Arrow Icon
Notes on Survival analysis Develop models for survival times Y . f ( y ) is its pdf and F ( y ) its distribution function. Survivor function : probability of survival beyond time y or S ( y ) = P [ Y > y ] = 1 - F ( y ) . Hazard function : probability of death in an infinitesimal interval given survival to time y We showed that the hazard h ( y ) satisfies h ( y ) = f ( y ) S ( y ) = - d dy [ log ( S ( y ))] May think of the survival function in terms of cummulative hazard H ( y ) . UNM
Image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
S ( y ) = exp ( - H ( y )) where H ( y ) = Z y 0 h ( t ) dt . Inference could be related to quantiles of F ( y ) (or S ( y ) ) q-quantile y ( q ) solution to the equation F ( y ( q )) = q or S ( y ( q )) = 1 - q Simplest parametric model is f ( y | θ ) = exp ( - θ y ); θ > 0 , y > 0 In particular its hazard function is simply θ (does not depend on y ). UNM
Image of page 2
Another one is the Weibull distribution. f ( y | λ, φ ) = λφ y λ - 1 exp ( - φ y λ ); y , λ, φ > 0 More flexible than exponential. In particular, its hazard function is h ( y | λ, φ ) = λφ y λ - 1 which is an ”accelerated failure time model”. It can be shown that for this distribution log ( - log ( S ( y | λ, φ ))) = log ( φ ) + λ log ( y ) A plot of log ( y ) values vs. empirical values of log ( - log ( S ( y | λ, φ ))) may suggest if the Weibull dist. is adequate. UNM
Image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Non-parametric estimation Empirical survivor function (without censoring). ˜ S ( y ) = number of subjects with time y total no. of subjects Step/decreasing function that starts at 1.
Image of page 4
Image of page 5
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

What students are saying

  • Left Quote Icon

    As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

    Student Picture

    Kiran Temple University Fox School of Business ‘17, Course Hero Intern

  • Left Quote Icon

    I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

    Student Picture

    Dana University of Pennsylvania ‘17, Course Hero Intern

  • Left Quote Icon

    The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

    Student Picture

    Jill Tulane University ‘16, Course Hero Intern