- 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:& Y1 l* F9 t) H. R# e, C6 R
, z* C. H J* |# p- F |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.
, y, `$ C1 b1 \3 j" K5 J- R
( g7 } \% A7 I; F: B; BNohe, 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.
! H1 o% a) [. p
# o2 e( G* p5 b- q在处理cross-level mediation的时侯,作者
l8 L7 B: k% L! J" q/ k“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] e% e) c9 ?; a; i# l
( g- |2 _1 d$ p; i
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. ! [' t4 {$ I! D4 v
( ?$ e6 p) [9 A$ K7 [' {4 Z' c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.”
: i7 I% @9 Q6 f. }- ~, }& Y
( v. _2 X8 M2 y) |; J+ n8 c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)。6 h( U+ a3 e3 J. k
Y4 f. j6 {- q: A _
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。
$ r1 _ c; L) h ^4 W8 G. p( [( M" {3 a' s4 |7 T( B9 s 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 N. m& U$ \2 @% Q! U! v
/ e) } u9 z* r/ G真诚希望得到您的指点!
3 r, P; ^0 y. u3 W0 U& h. J7 r+ ` e$ B) [
谢谢先! N0 T J2 d# K* e1 i
, C' A5 X) A( I# T: N9 z
q, Q0 N J( j2 N V' O6 @: ^
6 o9 b3 o) r. L' u4 Q) l- |% D1 _" ^9 Z
, L; @5 l' p' X1 p
F" O: H) a+ R/ r+ B7 D |
|