Assessment of Disagreement: A New Information-Based Approach

被引:27
作者
Costa-Santos, Cristina [1 ,4 ]
Antunes, Luis [3 ,5 ]
Souto, Andre [5 ]
Bernardes, Joao [2 ,6 ]
机构
[1] Univ Porto, Fac Med, Dept Biostat & Med Informat, P-4200319 Oporto, Portugal
[2] Univ Porto, Fac Med, Dept Obstet & Gynecol, P-4200319 Oporto, Portugal
[3] Univ Porto, Fac Sci, Dept Comp Sci, P-4200319 Oporto, Portugal
[4] Ctr Res Hlth Technol & Informat Syst, Oporto, Portugal
[5] Inst Telecomunicacoes, Oporto, Portugal
[6] Inst Biomed Engn, Oporto, Portugal
关键词
Observer Variation; Information Theory; Reproducibility of Results; INTRACLASS CORRELATION-COEFFICIENTS; CONCORDANCE CORRELATION-COEFFICIENT; EVALUATE REPRODUCIBILITY; AGREEMENT; VARIABLES;
D O I
10.1016/j.annepidem.2010.02.011
中图分类号
R1 [预防医学、卫生学];
学科分类号
1004 ; 120402 ;
摘要
PURPOSE: Disagreement on the interpretation of diagnostic tests and clinical decisions remains an important problem in medicine. As no strategy to assess agreement seems to be fail-safe to compare the degree of agreement, or disagreement, we propose a new information-based approach to assess disagreement. METHODS: The sum over all logarithms of possible outcomes of a variable is a valid measure of the amount of information contained in the variable. The proposed measure is based on the amount of information contained in the differences between two observations. This measure is normalized and satisfies the flowing properties: it is a metric, scaled invariant and it has differential weighting. RESULTS: Two real examples and a simulation were used to illustrate the usefulness of the proposed measure to compare the degree of disagreement. CONCLUSIONS: Used as complement to the existing methods, we believe our approach can be useful to compare the degree of disagreement among different populations. Ann Epidemiol 2010;20:555-561. (C) 2010 Elsevier Inc. All rights reserved.
引用
收藏
页码:555 / 561
页数:7
相关论文
共 20 条
[1]  
Atkinson G, 1997, BIOMETRICS, V53, P775
[2]  
Bland JM, 1999, STAT METHODS MED RES, V8, P135, DOI 10.1177/096228029900800204
[3]   STATISTICAL METHODS FOR ASSESSING AGREEMENT BETWEEN TWO METHODS OF CLINICAL MEASUREMENT [J].
BLAND, JM ;
ALTMAN, DG .
LANCET, 1986, 1 (8476) :307-310
[4]  
Bland M., 1995, INTRO MED STAT, V2nd
[5]   A NEW VIEW OF INTER-OBSERVER AGREEMENT [J].
BURDOCK, EI ;
FLEISS, JL ;
HARDESTY, AS .
PERSONNEL PSYCHOLOGY, 1963, 16 (04) :373-384
[6]  
DEVET H, 1999, ENCY BIOSTATISTICS, P3123
[7]   A review of five cardiology journals found that observer variability of measured variables was infrequently reported [J].
Gow, Robert M. ;
Barrowman, Nicholas J. ;
Lai, Lillian ;
Moher, David .
JOURNAL OF CLINICAL EPIDEMIOLOGY, 2008, 61 (04) :394-401
[8]   STATISTICAL EVALUATION OF AGREEMENT BETWEEN 2 METHODS FOR MEASURING A QUANTITATIVE VARIABLE [J].
LEE, J ;
KOH, D ;
ONG, CN .
COMPUTERS IN BIOLOGY AND MEDICINE, 1989, 19 (01) :61-70
[9]   A CONCORDANCE CORRELATION-COEFFICIENT TO EVALUATE REPRODUCIBILITY [J].
LIN, LI .
BIOMETRICS, 1989, 45 (01) :255-268
[10]   More than one statistical strategy to assess agreement of quantitative measurements may usefully be reported [J].
Luiz, RR ;
Szklo, M .
JOURNAL OF CLINICAL EPIDEMIOLOGY, 2005, 58 (03) :215-216