|
|
|
||||
|
|
|||||
* This is based on the example from Winer Page 288
. lis
j1 j2 j3 j4 pid
1. 2 4 3 3 1
2. 5 7 5 6 2
3. 1 3 1 2 3
4. 7 9 9 8 4
5. 2 4 6 1 5
6. 6 8 8 4 6
reshape long j, i(pid) j(judge)
(note: j = 1 2 3 4)
Data wide -> long
-----------------------------------------------------------------------------
Number of obs. 6 -> 24
Number of variables 5 -> 3
j variable (4 values) -> judge
xij variables:
j1 j2 ... j4 -> j
-----------------------------------------------------------------------------
lis
pid judge j
1. 1 1 2
2. 1 2 4
3. 1 3 3
4. 1 4 3
5. 2 1 5
6. 2 2 7
7. 2 3 5
8. 2 4 6
9. 3 1 1
10. 3 2 3
11. 3 3 1
12. 3 4 2
13. 4 1 7
14. 4 2 9
15. 4 3 9
16. 4 4 8
17. 5 1 2
18. 5 2 4
19. 5 3 6
20. 5 4 1
21. 6 1 6
22. 6 2 8
23. 6 3 8
24. 6 4 4
anova j pid judge
Number of obs = 24 R-squared = 0.8833
Root MSE = 1.11056 Adj R-squared = 0.8210
Source | Partial SS df MS F Prob > F
-----------+----------------------------------------------------
Model | 140.00 8 17.50 14.19 0.0000
|
pid | 122.50 5 24.50 19.86 0.0000
judge | 17.50 3 5.83333333 4.73 0.0162
|
Residual | 18.50 15 1.23333333
-----------+----------------------------------------------------
Total | 158.50 23 6.89130435
* You can then take the output from above and use the
* formulas on page 288 and 289 for computing the intraclass correlation.
UCLA Researchers are invited to our Statistical Consulting Services
We recommend others to our list of Other Resources for Statistical Computing Help
These pages are Copyrighted (c) by UCLA Academic Technology Services