Home  |  About us  |  Editorial board  |  Current issue  |  Archives  |  Submit article  |  Instructions  |  Subscribe  |  Advertise  |  Contacts  |  Login 
  Users Online: 407Home Print this page Email this page Small font sizeDefault font sizeIncrease font size  

 Table of Contents      
LETTER TO EDITOR
Year : 2012  |  Volume : 3  |  Issue : 1  |  Page : 40

Censoring in survival analysis: Potential for bias


1 Department of Anaesthesiology, Tata Memorial Hospital, Parel, Mumbai - 400 012, India
2 Department of Surgical Oncology, Tata Memorial Hospital, Parel, Mumbai - 400 012, India

Date of Web Publication25-Jan-2012

Correspondence Address:
Priya Ranganathan
Department of Anaesthesiology, Tata Memorial Hospital, Parel, Mumbai - 400 012
India
Login to access the Email id

Source of Support: None, Conflict of Interest: None


DOI: 10.4103/2229-3485.92307

Rights and Permissions

How to cite this article:
Ranganathan P, Pramesh C S. Censoring in survival analysis: Potential for bias. Perspect Clin Res 2012;3:40

How to cite this URL:
Ranganathan P, Pramesh C S. Censoring in survival analysis: Potential for bias. Perspect Clin Res [serial online] 2012 [cited 2017 Apr 25];3:40. Available from: http://www.picronline.org/text.asp?2012/3/1/40/92307

Sir,

We read with interest the article by Singh and Mukhopadhyay [1] on survival analysis. We commend the authors for simplifying a complex topic and for their in-depth explanation of the principles of survival analysis. However, the authors have failed to adequately emphasize one of the most important assumptions of censoring - which is that the censored patients are considered to have survival prospects similar to the participants who continued to be followed. [2]

Censoring in survival analysis should be "non-informative," i.e. participants who drop out of the study should do so due to reasons unrelated to the study. Informative censoring occurs when participants are lost to follow-up due to reasons related to the study, e.g. in a study comparing disease-free survival after two treatments for cancer, the control arm may be ineffective, leading to more recurrences and patients becoming too sick to follow-up. On the other hand, patients on the intervention arm may be completely cured by an effective treatment and may no longer feel the need to follow-up. If these participants are routinely censored, the true treatment effect will not be picked up and the results of the study will be biased. Disease-free survival rates would be based on the patients who continued to be followed-up in the study, and would be overestimated for the control arm and underestimated for the treatment arm.

Several methods have been described to deal with the problem of informative censoring. These include imputation techniques for missing data, sensitivity analyses to mimic best and worst-case scenarios and use of the drop-out event as a study end-point. [3] For unbiased analysis of survival curves, it is essential that censoring due to loss to follow-up should be minimal and truly "non-informative." Failure to understand these aspects of survival analysis could lead to grossly erroneous results from perfectly well-conducted studies.

 
   References Top

1.Singh R, Mukhopadhyay K. Survival analysis in clinical trials: Basics and must-know areas. Perspect Clin Res 2011;2:145-8.  Back to cited text no. 1
  Medknow Journal  
2.Bland JM, Altman D G. Survival probabilities (the Kaplan­Meier method). BMJ 1998;317:1572.  Back to cited text no. 2
    
3.Shih W. Problems in dealing with missing data and informative censoring in clinical trials. Curr Control Trials Cardiovasc Med 2002;3:4.  Back to cited text no. 3
[PUBMED]  [FULLTEXT]  



This article has been cited by
1 Adherence to Antiretroviral Therapy During and After Pregnancy: Cohort Study on Women Receiving Care in Malawięs Option B+ Program
Andreas D. Haas,Malango T. Msukwa,Matthias Egger,Lyson Tenthani,Hannock Tweya,Andreas Jahn,Oliver J. Gadabu,Kali Tal,Luisa Salazar-Vizcaya,Janne Estill,Adrian Spoerri,Nozgechi Phiri,Frank Chimbwandira,Joep J. van Oosterhout,Olivia Keiser
Clinical Infectious Diseases. 2016; : ciw500
[Pubmed] | [DOI]
2 Short-term cessation of sex work and injection drug use: Evidence from a recurrent event survival analysis
Tommi L. Gaines,Lianne A. Urada,Gustavo Martinez,Shira M. Goldenberg,Gudelia Rangel,Elizabeth Reed,Thomas L. Patterson,Steffanie A. Strathdee
Addictive Behaviors. 2015; 45: 63
[Pubmed] | [DOI]
3 A new comparison of nested case–control and case–cohort designs and methods
Ryung S. Kim
European Journal of Epidemiology. 2014;
[Pubmed] | [DOI]
4 Simulation studies on the estimation of total area under the curve in the presence of right-tailed censoring
Peter L. Bonate
Journal of Pharmacokinetics and Pharmacodynamics. 2014;
[Pubmed] | [DOI]
5 Comparison of Success Rates Using Video Laryngoscopy Versus Direct Laryngoscopy by Residents During a Simulated Pediatric Emergency
Michael J. Sylvia,Louise Maranda,Kathryn L. Harris,Jennifer Thompson,Barbara M. Walsh
Simulation in Healthcare: The Journal of the Society for Simulation in Healthcare. 2013; 8(3): 155
[Pubmed] | [DOI]



 

Top
  
 
  Search
 
    Similar in PUBMED
   Search Pubmed for
   Search in Google Scholar for
    Access Statistics
    Email Alert *
    Add to My List *
* Registration required (free)  

 
  In this article
    References

 Article Access Statistics
    Viewed6099    
    Printed86    
    Emailed2    
    PDF Downloaded428    
    Comments [Add]    
    Cited by others 5    

Recommend this journal