作者metrostar (台风夜的F1)
看板Statistics
标题[问题] 中介变项的成立
时间Sun Oct 4 13:40:25 2009
有个中介变项的相关问题想请问
使用了tnnstriker版友介绍的这个网页
http://www.comm.ohio-state.edu/ahayes/sobel.htm
跑中介变项的结果如下
直接与间接效果都显着
那是不是就是代表中介效果是存在的呢
un MATRIX procedure:
*************************************************************************
Preacher And Hayes (2004) SPSS Script For Simple Mediation
Written by Andrew F. Hayes, The Ohio State University
http://www.comm.ohio-state.edu/ahayes/
VARIABLES IN SIMPLE MEDIATION MODEL
Y T_C
X T_A
M T_B
DESCRIPTIVES STATISTICS AND PEARSON CORRELATIONS
Mean SD T_C T_A T_B
T_C 25.3205 6.9700 1.0000 .4344 .5386
T_A 45.3205 11.9039 .4344 1.0000 .2884
T_B 27.4038 10.1529 .5386 .2884 1.0000
SAMPLE SIZE
156
DIRECT And TOTAL EFFECTS
Coeff s.e. t Sig(two)
b(YX) .2543 .0425 5.9842 .0000
b(MX) .2460 .0658 3.7379 .0003
b(YM.X) .3095 .0458 6.7542 .0000
b(YX.M) .1782 .0391 4.5593 .0000
INDIRECT EFFECT And SIGNIFICANCE USING NORMAL DISTRIBUTION
Value s.e. LL 95 CI UL 95 CI Z Sig(two)
Effect .0761 .0235 .0301 .1221 3.2434 .0012
FAIRCHILD ET AL. (2009) VARIANCE IN Y ACCOUNTED FOR BY INDIRECT EFFECT:
.1038
********************************* NOTES **********************************
------ END MATRIX -----
--
※ 发信站: 批踢踢实业坊(ptt.cc)
◆ From: 114.45.100.242