Missing data assumptions and methods in a smoking cessation study

ABSTRACT Aim  A sizable percentage of subjects do not respond to follow‐up attempts in smoking cessation studies. The usual procedure in the smoking cessation literature is to assume that non‐respondents have resumed smoking. This study used data from a study with a high follow‐up rate to assess the...

Full description

Saved in:
Bibliographic Details
Published in:Addiction (Abingdon, England) England), 2010-03, Vol.105 (3), p.431-437
Main Authors: Barnes, Sunni A., Larsen, Michael D., Schroeder, Darrell, Hanson, Andrew, Decker, Paul A.
Format: Article
Language:English
Subjects:
Addiction
Addictive behaviors
Adult and adolescent clinical studies
Bias
Biological and medical sciences
Clinical Trials as Topic - standards
Data collection
Data Interpretation, Statistical
Data protection
Drug addiction
Follow-Up Studies
Humans
Informative censoring
LOCF
Medical sciences
Methodology
multiple imputation
non-response
Psychology. Psychoanalysis. Psychiatry
Psychopathology. Psychiatry
Research methods
Smoking
Smoking cessation
Smoking Cessation - statistics & numerical data
Tobacco smoking
Tobacco, tobacco smoking
Toxicology
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:ABSTRACT Aim  A sizable percentage of subjects do not respond to follow‐up attempts in smoking cessation studies. The usual procedure in the smoking cessation literature is to assume that non‐respondents have resumed smoking. This study used data from a study with a high follow‐up rate to assess the degree of bias that may be caused by different methods of imputing missing data. Design and methods  Based on a large data set with very little missing follow‐up information at 12 months, a simulation study was undertaken to compare and contrast missing data imputation methods (assuming smoking, propensity score matching and optimal matching) under various assumptions as to how the missing data arose (randomly generated missing values, increased non‐response from smokers and a hybrid of the two). Findings  Missing data imputation methods all resulted in some degree of bias which increased with the amount of missing data. Conclusion  None of the missing data imputation methods currently available can compensate for bias when there are substantial amounts of missing data.
ISSN:0965-2140
1360-0443
DOI:10.1111/j.1360-0443.2009.02809.x