rmac-package(rmac)
rmac-package()所属R语言包：rmac
Fixed and Random Marginal Agreement Coefficients
固定和随机边际协议系数
译者：生物统计家园网 机器人LoveR
描述----------Description----------
This package consists of four functions for calculating fixed and random marginal agreement coefficients based on the paper Fay (2005). The fixed marginal agreement coefficient (FMAC) is the traditional agreement coefficient, which assumes that each measurement's marginal distribution is the best estimate of its true distribution for the calculation of expected agreement due to chance. Examples of the fixed marginal agreement coefficient include the weighted kappa and the concordance coerrelation coefficient. In certain cases, fixed marginal agreement coefficients will indicated a high degree of agreement when the marginal distributions are extremely unbalanced (Feinstein and Cicchetti 1989). As an alternative to this, the Fay (2005) paper proposes the random marginal agreement coefficient (RMAC), which assumes that a mixture distribution of the two measurement distributions is the best estimate of both measurements' true distributions. For example, the paper uses the Westlund and Kurkland (1953) multiple sclerosis data. Patients were rated for likelihood of multiple sclerosis on a scale from 1 to 4 by two different neurologists. As the code below (see example section) shows, when the original data (msd1) is modified so that the 10 patients neurologist 1 awareded a score of "3" and neurologist 2 awarded a score of "1" receive a score of "1" from neurologist 1 and a score of "3" from neurologist 2, the FMAC changes, while the RMAC is the same.
这个软件包由四个固定的和随机的纸飞飞“（2005年）的基础上的的边际协议系数的计算功能。该的固定边际协议系数（FMAC）是传统的协议系数，假设每个测量的边缘分布是其真实分布的最佳估计数的计算由于偶然的预期协议。的固定的边际协议系数包括的加权kappa的一致性coerrelation系数的。在某些情况下，固定边际协议系数的边缘分布极不平衡（Feinstein和Cicchetti，1989），表明了高度的一致。作为替代，飞飞“（2005年）本文提出的随机边际协议的系数（RMAC），假设两个测量分布的混合分布的最佳估计这两种测量的真实分布。例如，使用Westlund和Kurkland（1953）多发性硬化症的数据。患者被评估为多发性硬化的可能性从1到4的规模上由两个不同的神经学家。下面的代码（例如部分）显示，当原始数据（msd1）进行修改，使10例患者神经学家1 awareded的得分，比分获得了“1”，“3”和神经学家2收到从神经学家1和从神经学家2，FMAC变化为“3”的得分的得分为“1”，，而RMAC是相同的。
Details
详细信息----------Details----------
License: </td><td align="left"> GPL2 </td> </tr> </td> </table>
经营许可证：</ TD> <TD ALIGN="LEFT"> GPL2 </ TD> </ TR> </ TD> </ TABLE>
（作者）----------Author(s)----------
Jennifer Kirk
Maintainer: Jennifer Kirk <jenn.kirk@nih.gov>
参考文献----------References----------
Cohen, J. (1960). A coefficient of agreement for nominal scales. Educ. Psychol. Meas., 20: 37-46.
Cohen, J. (1968). Weighted kappa: Nominal scale agreement with provision for scaled disagreement or partial credit. Psychol. Bull., 70: 213-220.
Fay, M.P. (2005). Random marginal agreement coefficients: Rethinking the adjustment for chance in agreement coefficients. Biostatistics, 6: 171-180.
Feinstein, A. R. and Cicchetti, D. V. (1989). High agreement but low kappa: I. the problems of two paradoxes. J. Clin. Epidemiol. 43: 543-549.
Lin, L. I. (1989) A concordance correlation coefficient to evaluate reproducibility. Biometrics. 45: 255-268. (Correction: 200, pp. 324-325)
Scott, W. A. (1955). Reliability of content analysis: The case of nominal scale coding. Public Opinion Quart., 19: 321-325.
Westlund, K. B. and Kurkland, L. T. (1953). Studies in multiple sclerosis in Winnipeg, Manitoba and New Orleans, Louisiana. American Journal of Hygiene. 57: 380-396.
参见----------See Also----------
wkappa, cac, rmacBoot
wkappa，cac，rmacBoot
实例----------Examples----------
#The Multiple Sclerosis Diagnoses Example (from Fay 2005)[多发性硬化症的诊断例（2005年由费伊）]
#the original data[的原始数据]
msd1<- as.table(matrix(data = c(38,5,0,1,33,11,3,0,10,14,5,6,3,7,3,10), 4,4, byrow = TRUE))
msd1
#the data with cell counts (1,3) and (3,1) reversed[用单元计数的数据（1,3）和（3,1）转回]
msd2<- as.table(matrix(data = c(38,5,10,1,33,11,3,0,0,14,5,6,3,7,3,10), 4,4, byrow = TRUE))
msd2
#calculate the FMAC of each data set[计算每个数据集的FMAC]
wkappa(msd1, method = "fmac")
wkappa(msd2, method = "fmac")
#calculate the FMAC of each data set[计算每个数据集的FMAC]
wkappa(msd1, method = "rmac")
wkappa(msd2, method = "rmac")
转载请注明:出自 生物统计家园网(http://www.biostatistic.net)。
注：
注1：为了方便大家学习，本文档为生物统计家园网机器人LoveR翻译而成，仅供个人R语言学习参考使用，生物统计家园保留版权。
注2：由于是机器人自动翻译，难免有不准确之处，使用时仔细对照中、英文内容进行反复理解，可以帮助R语言的学习。
注3：如遇到不准确之处，请在本贴的后面进行回帖，我们会逐渐进行修订。
|
发表于 2012-9-26 23:32:39
