- 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:+ O9 x! Q/ n T& q; X: j5 J
# F9 _' ?- _0 u
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. 3 E8 J& ]# Q# n- V4 `2 d- S
) Z) A! Y3 s% q
Nohe, 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.
7 H& h2 |% M6 t( x- L" U, ?
( E9 M5 o1 d1 d在处理cross-level mediation的时侯,作者
% g% W, f3 L# Q. ?3 Y# W7 _) K% e. h ^“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]* m8 R6 h' p7 `6 J% ~) z" C! U
+ D6 d9 ?( i0 c% Y: U
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. ; _ K/ D* ]/ t% q
D% I! a$ D% l) y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.”
4 o# c$ [# Z# n% k" `+ r+ _9 J0 X4 X2 y! K" }4 @
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)。
2 f5 _* G4 K, m: P8 S
' i9 k3 c& o; [9 E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。
7 {7 \8 i6 D/ n" I- p, l6 A4 ] ~0 i
; Z5 ] V1 ~# W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? , \9 N* y( k6 C7 ?% ?6 A8 D9 o
% D4 Z# ^) f5 H* _" M真诚希望得到您的指点!
& I$ N9 O% I) }; D
8 B7 t0 J; Z, V3 [ ?+ r7 i谢谢先!
# k; y- s5 C+ r' c- I6 S9 ^( d I& o, O: K2 V# N: L! O: W
+ J2 u0 W4 w1 n' w; I, c
% O$ }$ i9 T0 E. U$ W3 C
; v: M4 y* F. e& W
5 p; t6 E" T, \" |5 ~9 H: {- I* t: z6 J8 b: \+ I
|
|