- 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:
& c( A5 i- u: y9 y8 o: k7 P$ ~/ [5 n
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.
( Y9 B4 W, b J$ \: e: d5 A6 _6 P1 k1 a9 H4 h! w% }
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.
1 J4 _$ q$ H) C( S( L) ^* Z! N) k$ S3 e* |
在处理cross-level mediation的时侯,作者/ x( |7 P6 K7 L: R% L
“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]) O2 a3 a' q6 P
9 S- L! N+ C" w! F N9 Q
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. . s" i/ r: }$ j+ o. Y. f
4 L1 j" o, H; Q- B) r& k. F
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.”
v5 I; I1 g, u1 L6 o, f1 Z: q- g# o2 E9 z6 {0 |9 f$ e, P
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)。) T$ u7 }" c. q
3 c( T9 m3 V) l0 d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。 ; |1 i: V& r6 R" t" Y/ T) X
; ^& x. z+ R( r" \; P' P) b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? " c' \ J: G3 J% r2 C6 p" `
" g5 x5 L6 L2 W, D
真诚希望得到您的指点!6 ^: r+ [; i, v2 U4 k) z4 N
9 w' `( l! c' x谢谢先!$ R* S) o' q4 i5 z x; b/ ?
" v8 i9 O' A3 ]1 b& I( f& W7 d4 ?
$ n- ~4 W3 N. |5 H* [! ?* F% R/ p. Z( T5 e1 A9 M" r
O3 w8 Z8 s" R1 C# N* n
( e6 Q, z/ o4 I: i- u) w
/ [) f0 J0 w, e$ s% t7 Q" h |
|