- 最后登录
- 2014-9-15
- 注册时间
- 2013-11-14
- 威望
- 0
- 金钱
- 65
- 贡献
- 40
- 阅读权限
- 20
- 积分
- 105
- 日志
- 0
- 记录
- 0
- 帖子
- 17
- 主题
- 4
- 精华
- 0
- 好友
- 0
- 注册时间
- 2013-11-14
- 最后登录
- 2014-9-15
- 积分
- 105
- 精华
- 0
- 主题
- 4
- 帖子
- 17
|
罗老师好,想请教您一个问题:
# p% j+ j4 I5 U3 F" N$ e$ \) t) t" J+ a) S
我在Leadership Quaterly上面看到一篇文章,是用MSEM测试的 一个2-1-1-2 sequential mediation.
+ z! j( e2 o ~! B; M4 a9 Y8 o
6 A: D3 X% P7 f/ k& oNohe, C., Michaelis, B., Menges, J. I., Zhang, Z., & Sonntag, K. (2013). Charisma and organizational change: A multilevel study of perceived charisma, commitment to change, and team performance. The Leadership Quarterly, 24, 378-389.8 l3 R- G1 c- s( |) n2 n
" H: m3 k7 r0 U. w: C
在处理cross-level mediation的时侯,作者
: g! z) f4 A7 V$ W“decompose the variance of a variable into its latent within-unit component (within-team variance) and a latent between-unit component (between-team variance; Lüdtke et al., 2008; Muthén & Asparouhov, 2009). Relationships between these variance components can be modeled independently at each level through the specification of structural and measurement models.”[p.383]
* a' J8 _; n% c# R$ y, k3 }, Z9 T7 w: L- i7 t' W' C$ p* ~
按照这个方法,我用Mplus把level 1的variable 分别在Level 1和Level 2作为latent variable 建Model (两个level 1的variable,每个都由7个item来衡量),然后只用Level 2的coefficients来计算the indirect effect of sequential mediation.
+ A- X7 G! o; G, J. C9 J
8 H: Y4 m( C1 V3 R/ s虽然Mplus给出了coefficient的estimation和significance level,但是model整体“nonidentified”,然后Mplus report “THE NONIDENTIFICATION IS MOST LIKELY DUE TO HAVING MORE PARAMETERS THAN THE NUMBER OF CLUSTERS. REDUCE THE NUMBER OF PARAMETERS.”" g6 ? P) u% b8 |; R: ^
: P4 o4 O' H3 N7 G5 \2 E9 v+ m
我想这大概是主要因为每个latent variable的measure item比较多,可是group number只有39个的原因(虽然individual level sample 有1800多个)。
# z+ d6 O8 F9 Z6 d. k
/ ~ m9 r- Q- @7 R我试了另外一个model,不是用latent variable,而是用直接的aggregated variable分别在Level 1(mean of the 7 measure items) 和Level 2 (group average of the level 1 variable)参与模型运算。还是只看所有Level 2的coefficients来计算2-1-1-2的indirect sequential mediation。 Mplus就没有任何warning了。
w/ i8 X: C9 J$ |/ h! _5 c) u1 x7 t+ V" K' c
我想请问罗老师,如果我在limitation里面承认model有不完美的地方,我可以用我自己试的方法,不用latent variable,而是直接在Level 1和Level 2用aggregated value来计算一个2-1-1-2的模型么? % v2 r9 Q. K& C3 J3 I3 i" s W
8 B; ~! t C- B
真诚希望得到您的指点!4 }: [, V7 B8 o, v v0 E
& r+ [: s2 V% x! s, F, E# ^谢谢先!( G# g! Z+ O* p# g
! d: S' s- Y# m
# t% E% b# g* Z- y
' Q+ z& i; g0 |: C r# {4 M: n0 t: I- H' P9 @. q8 z* `
$ A) ~7 I$ F: P$ w5 f% W- z6 l' y# W% b L4 y, D/ n
|
|