Intraclass correlation

I would like to understand if the below data is suitable to implement IntraClass Correlation (ICC) or Single_random_raters or Single_fixed_raters. I have executed the below program in R generated different types of above mentioned output results. I am unable to decide which is the best suitable result for the data below. Please can someone expain?

GP_Id Pat_Id	Total_prescribed_prescriptions
1	a	1
1	b	2
1	c	4
1	d	1
1	e	2
2	f	7
2	g	2
2	h	1
2	i	7
3	j	8
3	k	9
3	l	4
3	m	6
3	n	4

Program1

library(psych)
ICC(R_COM)

output1

Intraclass correlation coefficients 
                         type      ICC    F  df1  df2    p lower bound upper bound
Single_raters_absolute   ICC1 -0.60834 0.24 4762 4763 1.00     -0.6231     -0.5931
Single_random_raters     ICC2  0.00065 1.01 4762 4762 0.43     -0.0051      0.0067
Single_fixed_raters      ICC3  0.00269 1.01 4762 4762 0.43     -0.0211      0.0265
Average_raters_absolute ICC1k -3.10647 0.24 4762 4763 1.00     -3.3070     -2.9153
Average_random_raters   ICC2k  0.00130 1.01 4762 4762 0.43     -0.0103      0.0132
Average_fixed_raters    ICC3k  0.00537 1.01 4762 4762 0.43     -0.0432      0.0517

Program2

library(psych)
ICC(R_COM)

Output 2

Single Score Intraclass Correlation

   Model: twoway 
   Type : agreement 

   Subjects = 4763 
     Raters = 2 
   ICC(A,1) = 0.000654

 F-Test, H0: r0 = 0 ; H1: r0 > 0 
F(4762,4447) = 1.01 , p = 0.428 

 95%-Confidence Interval for ICC Population Values:
  -0.006 < ICC < 0.008

This topic was automatically closed 21 days after the last reply. New replies are no longer allowed.

If you have a query related to it or one of the replies, start a new topic and refer back with a link.