Cover Image

An evaluation of statistical methods for determining agreement and reliability in medicine / Rafdzah Ahmad Zaki

Background and objective: Agreement and reliability are both important parameters in determining the quality of an instrument. The general aim of this study was to evaluate different statistical methods used to assess agreement and reliability of medical instruments that measure the same continuous...

Full description

Saved in:
Bibliographic Details
Main Author: Rafdzah Ahmad Zakibud, Abdullah
Format: Thesis
Published: 2013
Subjects:
R Medicine (General)
Online Access:http://studentsrepo.um.edu.my/5543/1/ThesisFinal_AN_EVALUATION_OF_STATISTICAL_METHODS.pdf
http://studentsrepo.um.edu.my/5543/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.um.stud.5543
record_format eprints
spelling my.um.stud.55432015-06-25T01:00:05Z An evaluation of statistical methods for determining agreement and reliability in medicine / Rafdzah Ahmad Zaki Rafdzah Ahmad Zakibud, Abdullah R Medicine (General) Background and objective: Agreement and reliability are both important parameters in determining the quality of an instrument. The general aim of this study was to evaluate different statistical methods used to assess agreement and reliability of medical instruments that measure the same continuous outcome. This study compares the most commonly used statistical methods, and also compares the proposed method in the analysis of agreement. Two separate systematic reviews were performed at the beginning of this study to identify the most popular method used to assess agreement and reliability of medical instruments. Methods: Two systematic reviews, one on agreement studies and another on reliability studies were carried out. A cross-sectional study was then conducted to collect data in two population settings; an institutional and community setting. Data were collected for blood glucose level, systolic blood pressure, diastolic blood pressure, body weight, and peak expiratory flow rate to assess methods used in agreement studies. Data were also collected for reliability studies. The variables for this were systolic blood pressure, diastolic blood pressure, heart rate, body temperature, peak expiratory flow rate and carbon monoxide level. Evaluations of agreement and reliability statistical methods were carried out on the original clinical data and simulated data. The agreement evaluation involved a comparison of the most commonly used methods (Bland-Altman Limits of Agreement and Intra-class Correlation Coefficient for agreement), comparison of slopes and y-intercepts analysis, and a new proposed agreement model. The reliability evaluation involved a comparison of the Bland-Altman Limits of Agreement, Intra-class Correlation Coefficient for consistency (ICCC), and Intra-class Correlation Coefficient for absolute agreement (ICCA). iii Results and Conclusion: The systematic reviews identified some issues related to method comparison studies including the application of inappropriate statistical methods, and the importance of education in method comparison studies among medical professionals. The evaluations of different statistical methods provided different conclusions on agreement and reliability. Each method was found to have its own strengths and weaknesses and no single method was found to be perfect. Several recommendations were made including optimal sample size for Bland-Altman analysis, and a proposed flowchart to guide analysis of agreement and reliability in method comparison studies. 2013 Thesis NonPeerReviewed application/pdf http://studentsrepo.um.edu.my/5543/1/ThesisFinal_AN_EVALUATION_OF_STATISTICAL_METHODS.pdf Rafdzah Ahmad Zakibud, Abdullah (2013) An evaluation of statistical methods for determining agreement and reliability in medicine / Rafdzah Ahmad Zaki. PhD thesis, University of Malaya. http://studentsrepo.um.edu.my/5543/
institution Universiti Malaya
building UM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Malaya
content_source UM Student Repository
url_provider http://studentsrepo.um.edu.my/
topic R Medicine (General)
spellingShingle R Medicine (General)
Rafdzah Ahmad Zakibud, Abdullah
An evaluation of statistical methods for determining agreement and reliability in medicine / Rafdzah Ahmad Zaki
description Background and objective: Agreement and reliability are both important parameters in determining the quality of an instrument. The general aim of this study was to evaluate different statistical methods used to assess agreement and reliability of medical instruments that measure the same continuous outcome. This study compares the most commonly used statistical methods, and also compares the proposed method in the analysis of agreement. Two separate systematic reviews were performed at the beginning of this study to identify the most popular method used to assess agreement and reliability of medical instruments. Methods: Two systematic reviews, one on agreement studies and another on reliability studies were carried out. A cross-sectional study was then conducted to collect data in two population settings; an institutional and community setting. Data were collected for blood glucose level, systolic blood pressure, diastolic blood pressure, body weight, and peak expiratory flow rate to assess methods used in agreement studies. Data were also collected for reliability studies. The variables for this were systolic blood pressure, diastolic blood pressure, heart rate, body temperature, peak expiratory flow rate and carbon monoxide level. Evaluations of agreement and reliability statistical methods were carried out on the original clinical data and simulated data. The agreement evaluation involved a comparison of the most commonly used methods (Bland-Altman Limits of Agreement and Intra-class Correlation Coefficient for agreement), comparison of slopes and y-intercepts analysis, and a new proposed agreement model. The reliability evaluation involved a comparison of the Bland-Altman Limits of Agreement, Intra-class Correlation Coefficient for consistency (ICCC), and Intra-class Correlation Coefficient for absolute agreement (ICCA). iii Results and Conclusion: The systematic reviews identified some issues related to method comparison studies including the application of inappropriate statistical methods, and the importance of education in method comparison studies among medical professionals. The evaluations of different statistical methods provided different conclusions on agreement and reliability. Each method was found to have its own strengths and weaknesses and no single method was found to be perfect. Several recommendations were made including optimal sample size for Bland-Altman analysis, and a proposed flowchart to guide analysis of agreement and reliability in method comparison studies.
format Thesis
author Rafdzah Ahmad Zakibud, Abdullah
author_facet Rafdzah Ahmad Zakibud, Abdullah
author_sort Rafdzah Ahmad Zakibud, Abdullah
title An evaluation of statistical methods for determining agreement and reliability in medicine / Rafdzah Ahmad Zaki
title_short An evaluation of statistical methods for determining agreement and reliability in medicine / Rafdzah Ahmad Zaki
title_full An evaluation of statistical methods for determining agreement and reliability in medicine / Rafdzah Ahmad Zaki
title_fullStr An evaluation of statistical methods for determining agreement and reliability in medicine / Rafdzah Ahmad Zaki
title_full_unstemmed An evaluation of statistical methods for determining agreement and reliability in medicine / Rafdzah Ahmad Zaki
title_sort evaluation of statistical methods for determining agreement and reliability in medicine / rafdzah ahmad zaki
publishDate 2013
url http://studentsrepo.um.edu.my/5543/1/ThesisFinal_AN_EVALUATION_OF_STATISTICAL_METHODS.pdf
http://studentsrepo.um.edu.my/5543/
_version_ 1738505803152752640
score 13.211869

Similar Items