- 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:
. ]# r, G9 W4 E% ~
0 t) ^) a4 j# X& E: l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.
, [' O% S3 Y) \2 L5 v: C8 d2 u8 q! y) q" c
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, 378-389.4 k9 }: Z* D3 M5 u, L3 o
$ g* T [0 J: q" w在处理cross-level mediation的时侯,作者2 ]7 f/ Z( {( q
“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]+ n( J8 s. c! e2 J2 J
. h9 ^% Q# |+ h! a0 ]. K' ]$ F
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.
9 N# z4 K' R. W
* G/ F! i' u- ?& ~" 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.”
" J) o* y# G2 W0 q7 K8 r# L. y4 i( z& N1 z, K6 U3 h3 i
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)。; s, o4 p) @, u1 Q% F/ d* g; V. p4 c
8 x. \1 ]8 C& f0 |% z: }2 K
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。
6 }' t% t0 C' j6 V& p
! e, P# h9 k* b) V! D+ |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?
0 |, \$ E B7 V0 }9 x. T2 c' i" c. s: Z, g3 H8 ]- R
真诚希望得到您的指点!3 \( w4 s: P, @6 |
; @2 P' e' g( L* s1 X4 u4 U
谢谢先!
$ e4 w* o( L% h/ l* M3 M& h
8 K+ r& P0 _% }2 Z, ]1 ~' J0 w. K# z/ d O7 }' q i( ^, y5 L
2 p5 S$ q# ]% G$ a! A
3 G; m9 n' V1 D) {
5 u/ |1 Y$ l, i
' X) ~: p3 r( o! S3 H2 w d0 g) F |
|