A Bayesian method of estimating kappa coefficient with application to a rheumatoid arthritis study. (English) Zbl 1177.62037
Summary: We provide estimates of the kappa coefficient using multivariate probit models from a Bayesian perspective and investigate the performance of our method by assuming different prior distributions for the correlations of the underlying normal variables from multivariate probit models. We compare our method with J. L. Fleiss’ method [Psychol. Bull. 76, 378–382 (1971)] and the weighted moment method through two simulation studies. We further show that our method can be easily extended to detect treatment effects and estimate the kappa coefficients by treatment groups for clustered binary data using an example from an immunotherapy study in rheumatoid arthritis. C-code for our program is available on request.
MSC:
62F15 | Bayesian inference |
92C50 | Medical applications (general) |
65C40 | Numerical analysis or methods applied to Markov chains |
65C60 | Computational problems in statistics (MSC2010) |
Keywords:
kappa coefficient; Markov chain Monte Carlo; multivariate probit model; rheumatoid arthritis; simulation study; tetrachoric correlation; tablesSoftware:
boaReferences:
[1] | DOI: 10.2307/2290350 · Zbl 0774.62031 · doi:10.2307/2290350 |
[2] | DOI: 10.2307/3315487 · Zbl 0929.62117 · doi:10.2307/3315487 |
[3] | DOI: 10.2307/2532907 · Zbl 0875.62533 · doi:10.2307/2532907 |
[4] | DOI: 10.1111/j.0006-341X.2000.00577.x · Zbl 1060.62507 · doi:10.1111/j.0006-341X.2000.00577.x |
[5] | DOI: 10.2307/2532052 · Zbl 0715.62113 · doi:10.2307/2532052 |
[6] | DOI: 10.1081/STA-100002038 · Zbl 1054.62526 · doi:10.1081/STA-100002038 |
[7] | DOI: 10.1093/biomet/85.2.347 · Zbl 0938.62020 · doi:10.1093/biomet/85.2.347 |
[8] | DOI: 10.1177/001316446002000104 · doi:10.1177/001316446002000104 |
[9] | DOI: 10.1037/h0026256 · doi:10.1037/h0026256 |
[10] | Drasgow F., Encyclopedia of Statistical Sciences 7 pp 69– (1988) |
[11] | DOI: 10.1002/art.1780380602 · doi:10.1002/art.1780380602 |
[12] | DOI: 10.1037/h0031619 · doi:10.1037/h0031619 |
[13] | DOI: 10.1002/sim.4780111304 · doi:10.1002/sim.4780111304 |
[14] | DOI: 10.1002/sim.2877 · doi:10.1002/sim.2877 |
[15] | DOI: 10.2307/2532564 · doi:10.2307/2532564 |
[16] | DOI: 10.1002/sim.1180 · doi:10.1002/sim.1180 |
[17] | DOI: 10.2307/1390914 · doi:10.2307/1390914 |
[18] | DOI: 10.2307/2986022 · Zbl 0825.62891 · doi:10.2307/2986022 |
[19] | DOI: 10.1198/10618600152418746 · doi:10.1198/10618600152418746 |
[20] | DOI: 10.1002/bimj.200390021 · doi:10.1002/bimj.200390021 |
[21] | DOI: 10.1111/j.0006-341X.2000.00583.x · Zbl 1060.62561 · doi:10.1111/j.0006-341X.2000.00583.x |
[22] | Nandram B., J. Statist. Computat. Simul. 81 pp 27– (1994) |
[23] | DOI: 10.1093/biomet/71.3.531 · Zbl 0569.62094 · doi:10.1093/biomet/71.3.531 |
[24] | DOI: 10.1002/sim.1142 · doi:10.1002/sim.1142 |
[25] | DOI: 10.1098/rsta.1900.0022 · JFM 32.0238.01 · doi:10.1098/rsta.1900.0022 |
[26] | Reid , J. B. , Roberts , D. M. ( 1978 ). A Monte Carlo comparison of Phi and Kappa as measures of criterion-referenced reliability. 62nd. Ann. Mtg. Amer. Educat. Res. Assoc. Toronto, Ontario, Canada, March 27–31 . |
[27] | Smith , B. J. ( 2005 ). Bayesian output analysis program (BOA) version 1.1 user’s manual. http://www.public-health.uiowa.edu/boa . |
[28] | Uebersax , J. S. ( 2006 ). The tetrachoric and polychoric correlation coefficients. Statistical Methods for Rater Agreement web site.http://ourworld.compuserve.com/ homepages/jsuebersax/tetra.htm . |
[29] | DOI: 10.1198/106186006X160050 · doi:10.1198/106186006X160050 |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.