Reliability study designer

Calculation of the number of required subjects and replications in a reliability assessment

File name : 'Shoukri.m'. This file can be used
for calculating the required number of subjects
at a desired kappa value for reliability
assessment.
Five input values : 'alfa', 'omega', 'pi', 'rho' and 'kappa'
Three output value : 'k', 'n' and 'N'
alfa : significance level (value between 0 and 1)
omega : desired interval of kappa (value between 0 and 1)
pi : probability of positive rating (value between 0 and 1)
rho : within-subject interclass correlation
kappa : desired coefficient of agreement (value between 0 and 1)

k : number of subjects (value larger than 1)
n : number of replication (value equal to or larger than 1)
N : number of allocations (value larger than 1)
Figure : plot of the number of subjects versus the number of replications
Input syntax : Shoukri(alfa,omega,pi,kappa)
NOTE: No default values are set
REFERENCES
[1] : Shoukri, M. M. (2010). Measures of interobserver agreement and reliability: CRC Press.
[2] : Landis, J. R., & Koch, G. G. (1977). The measurement of observer agreement for categorical data. Biometrics, 159-174.
[3] : Shoukri, M., Asyali, M. & Walter, S. (2003). Issues of cost and efficiency in the design of reliability studies. biometrics. 59(4): p. 1107-1112.
[4] : Cohen, J. (1960). A coefficient of agreement for nominal scales. Educational and psychological measurement. 20(1): p. 37-46

Developed by Joris Meurs BASc (2015)