- 最后登录
- 2016-11-27
- 注册时间
- 2003-1-21
- 威望
- 250
- 金钱
- 16832
- 贡献
- 11934
- 阅读权限
- 255
- 积分
- 29016
- 日志
- 4
- 记录
- 0
- 帖子
- 1438
- 主题
- 69
- 精华
- 0
- 好友
- 380
- 注册时间
- 2003-1-21
- 最后登录
- 2016-11-27
- 积分
- 29016
- 精华
- 0
- 主题
- 69
- 帖子
- 1438
|
本帖最后由 Kenneth 于 2012-2-2 13:47 编辑 ! z! w+ N" `8 `
玄兔子和夏桃 发表于 2012-2-1 15:59
3 e/ r8 a" d9 r" FKenneth,ICC(1)的值是不是应该在0.2左右才说明小组加总是可行的?
# o# P: m4 A8 I9 l* |对于ICC(1):) H* i1 q& b& c" R. K& d
“We encourage researchers to adopt traditional conventions used when interpreting effect sizes (i.e., percentage of variance explained). Specifically, a value of .01 might be considered a ‘small’ effect, a value of .10 might be considered a ‘medium’ effect, and a value of .25 might be considered a ‘large’ effect“' @- I& a8 U. [. o
; M( a5 o, d/ A) w9 l; \$ w
对于ICC(2):
, s7 z9 X5 F5 HSo in most instances, ICC(K) and ICC(A,K) values >.90 are likely unnecessary. However, depending on the quality of the measures being used in multilevel analysis, researchers will probably want to choose between .70 and .85 to justify aggregation.”
# ]% `0 I Q4 `5 \: F5 Y7 c( W1 v% K- G6 T
Reference:
6 u: U' w) W# ]0 t4 |LeBreton, J.M. & Senter, J.L. (2008). Answers to 20 questions about interrater reliability and interrater agreement. Organizational Research Methods, 11(4), 838-839.
' i/ L* M$ X3 l |
|