Advanced Statistics: Missing Data in Clinical Research-Part 1: An Introduction and Conceptual Framework

Jason S. Haukoos, Craig Newgard

Research output: Contribution to journalArticle

107 Citations (Scopus)

Abstract

Missing data are commonly encountered in clinical research. Unfortunately, they are often neglected or not properly handled during analytic procedures, and this may substantially bias the results of the study, reduce study power, and lead to invalid conclusions. In this two-part series, the authors will introduce key concepts regarding missing data in clinical research, provide a conceptual framework for how to approach missing data in this setting, describe typical mechanisms and patterns of censoring of data and their relationships to specific methods of handling incomplete data, and describe in detail several simple and more complex methods of handling such data. In part 1, the authors will describe relatively simple approaches to handling missing data, including complete-case analysis, available-case analysis, and several forms of single imputation, including mean imputation, regression imputation, hot and cold deck imputation, last observation carried forward, and worst case analysis. In part 2, the authors will describe in detail multiple imputation, a more sophisticated and valid method for handling missing data.

Original languageEnglish (US)
Pages (from-to)662-668
Number of pages7
JournalAcademic Emergency Medicine
Volume14
Issue number7
DOIs
StatePublished - Jul 2007
Externally publishedYes

Fingerprint

Research
Observation

Keywords

  • bias
  • clinical research
  • complete-case analysis
  • hot deck imputation
  • imputation
  • last observation carried forward
  • mean imputation
  • missing data
  • regression imputation
  • single imputation
  • statistical analysis
  • worst case analysis

ASJC Scopus subject areas

  • Emergency Medicine

Cite this

Advanced Statistics : Missing Data in Clinical Research-Part 1: An Introduction and Conceptual Framework. / Haukoos, Jason S.; Newgard, Craig.

In: Academic Emergency Medicine, Vol. 14, No. 7, 07.2007, p. 662-668.

Research output: Contribution to journalArticle

@article{ca5f874fc67d42f7afc6425d07a2cd51,
title = "Advanced Statistics: Missing Data in Clinical Research-Part 1: An Introduction and Conceptual Framework",
abstract = "Missing data are commonly encountered in clinical research. Unfortunately, they are often neglected or not properly handled during analytic procedures, and this may substantially bias the results of the study, reduce study power, and lead to invalid conclusions. In this two-part series, the authors will introduce key concepts regarding missing data in clinical research, provide a conceptual framework for how to approach missing data in this setting, describe typical mechanisms and patterns of censoring of data and their relationships to specific methods of handling incomplete data, and describe in detail several simple and more complex methods of handling such data. In part 1, the authors will describe relatively simple approaches to handling missing data, including complete-case analysis, available-case analysis, and several forms of single imputation, including mean imputation, regression imputation, hot and cold deck imputation, last observation carried forward, and worst case analysis. In part 2, the authors will describe in detail multiple imputation, a more sophisticated and valid method for handling missing data.",
keywords = "bias, clinical research, complete-case analysis, hot deck imputation, imputation, last observation carried forward, mean imputation, missing data, regression imputation, single imputation, statistical analysis, worst case analysis",
author = "Haukoos, {Jason S.} and Craig Newgard",
year = "2007",
month = "7",
doi = "10.1197/j.aem.2006.11.037",
language = "English (US)",
volume = "14",
pages = "662--668",
journal = "Academic Emergency Medicine",
issn = "1069-6563",
publisher = "Wiley-Blackwell",
number = "7",

}

TY - JOUR

T1 - Advanced Statistics

T2 - Missing Data in Clinical Research-Part 1: An Introduction and Conceptual Framework

AU - Haukoos, Jason S.

AU - Newgard, Craig

PY - 2007/7

Y1 - 2007/7

N2 - Missing data are commonly encountered in clinical research. Unfortunately, they are often neglected or not properly handled during analytic procedures, and this may substantially bias the results of the study, reduce study power, and lead to invalid conclusions. In this two-part series, the authors will introduce key concepts regarding missing data in clinical research, provide a conceptual framework for how to approach missing data in this setting, describe typical mechanisms and patterns of censoring of data and their relationships to specific methods of handling incomplete data, and describe in detail several simple and more complex methods of handling such data. In part 1, the authors will describe relatively simple approaches to handling missing data, including complete-case analysis, available-case analysis, and several forms of single imputation, including mean imputation, regression imputation, hot and cold deck imputation, last observation carried forward, and worst case analysis. In part 2, the authors will describe in detail multiple imputation, a more sophisticated and valid method for handling missing data.

AB - Missing data are commonly encountered in clinical research. Unfortunately, they are often neglected or not properly handled during analytic procedures, and this may substantially bias the results of the study, reduce study power, and lead to invalid conclusions. In this two-part series, the authors will introduce key concepts regarding missing data in clinical research, provide a conceptual framework for how to approach missing data in this setting, describe typical mechanisms and patterns of censoring of data and their relationships to specific methods of handling incomplete data, and describe in detail several simple and more complex methods of handling such data. In part 1, the authors will describe relatively simple approaches to handling missing data, including complete-case analysis, available-case analysis, and several forms of single imputation, including mean imputation, regression imputation, hot and cold deck imputation, last observation carried forward, and worst case analysis. In part 2, the authors will describe in detail multiple imputation, a more sophisticated and valid method for handling missing data.

KW - bias

KW - clinical research

KW - complete-case analysis

KW - hot deck imputation

KW - imputation

KW - last observation carried forward

KW - mean imputation

KW - missing data

KW - regression imputation

KW - single imputation

KW - statistical analysis

KW - worst case analysis

UR - http://www.scopus.com/inward/record.url?scp=34250689552&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34250689552&partnerID=8YFLogxK

U2 - 10.1197/j.aem.2006.11.037

DO - 10.1197/j.aem.2006.11.037

M3 - Article

C2 - 17538078

AN - SCOPUS:34250689552

VL - 14

SP - 662

EP - 668

JO - Academic Emergency Medicine

JF - Academic Emergency Medicine

SN - 1069-6563

IS - 7

ER -