Bias in the last observation carried forward method under informative dropout

Chandan Saha, Michael P. Jones

Research output: Contribution to journalArticle

25 Citations (Scopus)

Abstract

Subject dropout is an inevitable problem in longitudinal studies. It makes the analysis challenging when the main interest is the change in outcome from baseline to endpoint of study. The last observation carried forward (LOCF) method is a very common approach for handling this problem. It assumes that the last measured outcome is frozen in time after the point of dropout, an unrealistic assumption given any time trends. Though existence and direction of the bias can sometimes be anticipated, the more important statistical question involves the actual magnitude of the bias and this requires computation. This paper provides explicit expressions for the exact bias in the LOCF estimates of mean change and its variance when the longitudinal data follow a linear mixed-effects model with linear time trajectories. General dropout patterns are considered that may depend on treatment group, subject-specific trajectories and follow different time to dropout distributions. In our case studies, the magnitude of bias for mean change estimators linearly increases as time to dropout decreases. The bias depends heavily on the dropout interval. The variance term is always underestimated.

Original languageEnglish (US)
Pages (from-to)246-255
Number of pages10
JournalJournal of Statistical Planning and Inference
Volume139
Issue number2
DOIs
StatePublished - Feb 1 2009

Fingerprint

Informative Dropout
Drop out
Trajectories
Trajectory
Linear Mixed Effects Model
Longitudinal Study
Longitudinal Data
Observation
Linear Time
Baseline
Linearly
Estimator
Decrease
Interval
Term
Estimate

Keywords

  • Clinical trial
  • Incomplete data
  • Informative dropout
  • LOCF
  • Longitudinal study
  • Repeated measurements

ASJC Scopus subject areas

  • Statistics, Probability and Uncertainty
  • Applied Mathematics
  • Statistics and Probability

Cite this

Bias in the last observation carried forward method under informative dropout. / Saha, Chandan; Jones, Michael P.

In: Journal of Statistical Planning and Inference, Vol. 139, No. 2, 01.02.2009, p. 246-255.

Research output: Contribution to journalArticle

@article{debda7b46d104d7b9626d912d5f2e8d5,
title = "Bias in the last observation carried forward method under informative dropout",
abstract = "Subject dropout is an inevitable problem in longitudinal studies. It makes the analysis challenging when the main interest is the change in outcome from baseline to endpoint of study. The last observation carried forward (LOCF) method is a very common approach for handling this problem. It assumes that the last measured outcome is frozen in time after the point of dropout, an unrealistic assumption given any time trends. Though existence and direction of the bias can sometimes be anticipated, the more important statistical question involves the actual magnitude of the bias and this requires computation. This paper provides explicit expressions for the exact bias in the LOCF estimates of mean change and its variance when the longitudinal data follow a linear mixed-effects model with linear time trajectories. General dropout patterns are considered that may depend on treatment group, subject-specific trajectories and follow different time to dropout distributions. In our case studies, the magnitude of bias for mean change estimators linearly increases as time to dropout decreases. The bias depends heavily on the dropout interval. The variance term is always underestimated.",
keywords = "Clinical trial, Incomplete data, Informative dropout, LOCF, Longitudinal study, Repeated measurements",
author = "Chandan Saha and Jones, {Michael P.}",
year = "2009",
month = "2",
day = "1",
doi = "10.1016/j.jspi.2008.04.017",
language = "English (US)",
volume = "139",
pages = "246--255",
journal = "Journal of Statistical Planning and Inference",
issn = "0378-3758",
publisher = "Elsevier",
number = "2",

}

TY - JOUR

T1 - Bias in the last observation carried forward method under informative dropout

AU - Saha, Chandan

AU - Jones, Michael P.

PY - 2009/2/1

Y1 - 2009/2/1

N2 - Subject dropout is an inevitable problem in longitudinal studies. It makes the analysis challenging when the main interest is the change in outcome from baseline to endpoint of study. The last observation carried forward (LOCF) method is a very common approach for handling this problem. It assumes that the last measured outcome is frozen in time after the point of dropout, an unrealistic assumption given any time trends. Though existence and direction of the bias can sometimes be anticipated, the more important statistical question involves the actual magnitude of the bias and this requires computation. This paper provides explicit expressions for the exact bias in the LOCF estimates of mean change and its variance when the longitudinal data follow a linear mixed-effects model with linear time trajectories. General dropout patterns are considered that may depend on treatment group, subject-specific trajectories and follow different time to dropout distributions. In our case studies, the magnitude of bias for mean change estimators linearly increases as time to dropout decreases. The bias depends heavily on the dropout interval. The variance term is always underestimated.

AB - Subject dropout is an inevitable problem in longitudinal studies. It makes the analysis challenging when the main interest is the change in outcome from baseline to endpoint of study. The last observation carried forward (LOCF) method is a very common approach for handling this problem. It assumes that the last measured outcome is frozen in time after the point of dropout, an unrealistic assumption given any time trends. Though existence and direction of the bias can sometimes be anticipated, the more important statistical question involves the actual magnitude of the bias and this requires computation. This paper provides explicit expressions for the exact bias in the LOCF estimates of mean change and its variance when the longitudinal data follow a linear mixed-effects model with linear time trajectories. General dropout patterns are considered that may depend on treatment group, subject-specific trajectories and follow different time to dropout distributions. In our case studies, the magnitude of bias for mean change estimators linearly increases as time to dropout decreases. The bias depends heavily on the dropout interval. The variance term is always underestimated.

KW - Clinical trial

KW - Incomplete data

KW - Informative dropout

KW - LOCF

KW - Longitudinal study

KW - Repeated measurements

UR - http://www.scopus.com/inward/record.url?scp=55149092319&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=55149092319&partnerID=8YFLogxK

U2 - 10.1016/j.jspi.2008.04.017

DO - 10.1016/j.jspi.2008.04.017

M3 - Article

AN - SCOPUS:55149092319

VL - 139

SP - 246

EP - 255

JO - Journal of Statistical Planning and Inference

JF - Journal of Statistical Planning and Inference

SN - 0378-3758

IS - 2

ER -