Korean J Anesthesiol Search


Korean J Anesthesiol > Epub ahead of print
DOI: https://doi.org/10.4097/kja.19183    [Epub ahead of print]
Published online May 17, 2019.
Survival Analysis: Part II - Methods reducing a gap between statistics and real world
Junyong In1  , Dong Kyu Lee2 
1Department of Anesthesiology and Pain Medicine, Dongguk University Ilsan Hospital, Goyang, Rep. of Korea
2Department of Anesthesiology and Pain Medicine, Korea University Medical Center Guro Hospital, Seoul, Rep. of Korea
Corresponding author:  Dong Kyu Lee, Tel: +82-2-2626-3237, Fax: +82-2-2626-1438, 
Email: entopic@korea.ac.kr
Received: 2 May 2019   • Revised: 13 May 2019   • Accepted: 16 May 2019
Following the previous article, this review provides several in-depth concepts of survival analysis. Also, several code for the specific survival analysis are also listed to enhance the understanding about survival analysis and to provide the applicable method for survival analysis. Proportional hazard assumption is one of important concepts in survival analysis. Validation of this assumption is crucial for survival analysis. For this purpose, graphical analysis method and the goodness of fit test are introduced with detailed code and examples. In case of the violated proportional hazard assumption, the extended models of Cox regression are required. The simplified concepts of stratified Cox proportional hazard model and time-dependent Cox regression are also described. Source code for actual analysis in available statistical package with detailed results interpretation could enable to realize survival analysis with personal data. To enhance statistical power of survival analysis, evaluation about basic assumptions and interaction between variables and time is important. By doing this, survival analysis could provide a reliable scientific result with confidence.
Key Words: Survival analysis; Proportional hazard assumption; Log-rank test; Cox regression; Log minus log plot; Goodness of fit test; Schoenfeld residual; Extended Cox regression; Stratified Cox regression; Time-dependent Cox regression
Share :
Facebook Twitter Linked In Google+ Line it
METRICS Graph View
  • 0 Crossref
  • 237 View
  • 60 Download


Browse all articles >

Editorial Office
101-3503, Lotte Castle President, 109 Mapo-daero, Mapo-gu, Seoul 04146, Korea
Tel: +82-2-795-5129    Fax: +82-2-792-4089    E-mail: anesthesia@kams.or.kr                

Copyright © 2019 by Korean Society of Anesthesiologists. All rights reserved.

Developed in M2community

Close layer
prev next