- 最后登录
- 2013-9-16
- 注册时间
- 2010-4-15
- 威望
- 4
- 金钱
- 6132
- 贡献
- 1573
- 阅读权限
- 90
- 积分
- 7709
- 日志
- 0
- 记录
- 0
- 帖子
- 610
- 主题
- 33
- 精华
- 0
- 好友
- 23
     
- 注册时间
- 2010-4-15
- 最后登录
- 2013-9-16
- 积分
- 7709
- 精华
- 0
- 主题
- 33
- 帖子
- 610
|
本帖最后由 jkliang 于 2012-9-13 17:42 编辑
: H$ i2 Q- q5 X' G
8 W: s2 p! V4 f( U4 G! ?; j; T在某個SPSS問答網頁中尋得以下答案,請參考。4 h$ h: b( f9 H. c% T
7 E) a) A% n4 \& o
The pattern matrix elements are analogous to the standardized regression coefficients from a
: y2 l9 Z3 r$ A% s' R. ?# Nmultiple regression. A given element of the pattern matrix indicates the importance of that
3 }7 p6 v" o/ r3 X4 Uvariable to the factor with the influence of the other variables partialled out.
3 p, x: ]% z- W: g! \- X0 } X( X' I9 u* U9 u! q1 P% Z. i
`6 Z* x! D: H$ b" k6 I) ]
The structure matrix elements are simple correlations of the variables with the factors. They reflect all
8 l3 H. z( g D' apaths from a factor to a variable (this includes factor to factor paths, since factors are correlated), while the2 E5 {4 Y1 v% a' K+ X" e
pattern coefficients reflect only the direct path from a factor to a variable.
u0 Q \# g7 }) s5 o4 A% x" } I6 Z7 Y4 s) n3 B1 W3 V
5 T* K, _- B) d9 q |
|