Re: [問題] lisrel配適度分析問題
※ 引述《mld7558 (amy)》之銘言：
目前正在進行配適分析，
但配適指標的卡方、RMSEA與NNF皆未達到標準，
因此要針對MI量表將不適的題項刪除，
但MI量表只出現"No Non-Zero Modification Indices for LAMBDA-X"
所以想請問：
為何MI量表沒有出現？
是哪裡發生錯誤?
如何才能達到配飾指標呢？
謝謝！！！！！！！！！
報表內容：
title :AT
data NI=5 NO=384 MA=KM
KM SY FI=C:\Users\amy\Desktop\0417\LISREL2\AT\AT.COR
LA; 1 2 3 4 5
MODEL NX=5 NK=1 LX=FU,FI TD=DI,FR
LK; ATITUDE
FREE LX(1,1) LX(2,1) LX(3,1) LX(4,1) LX(5,1)
FIX PH(1,1)
VALUE 1 PH(1,1)
PD
OUTPUT SE TV RS MR FS EF SS SC MI AD>50
AT
Number of Input Variables 5
Number of Y - Variables 0
Number of X - Variables 5
Number of ETA - Variables 0
Number of KSI - Variables 1
Number of Observations 384
LISREL Estimates (Maximum Likelihood)
LAMBDA-X
ATITUDE
--------
1 0.74
(0.05)
16.21
2 0.65
(0.05)
13.60
3 0.78
(0.04)
17.30
4 0.80
(0.04)
18.04
5 0.84
(0.04)
19.24
Goodness of Fit Statistics
Degrees of Freedom = 5
Minimum Fit Function Chi-Square = 102.65 (P = 0.0)
Normal Theory Weighted Least Squares Chi-Square = 114.27 (P = 0.0)
Estimated Non-centrality Parameter (NCP) = 109.27
90 Percent Confidence Interval for NCP = (78.13 ; 147.84)
Minimum Fit Function Value = 0.27
Population Discrepancy Function Value (F0) = 0.29
90 Percent Confidence Interval for F0 = (0.20 ; 0.39)
Root Mean Square Error of Approximation (RMSEA) = 0.24
90 Percent Confidence Interval for RMSEA = (0.20 ; 0.28)
P-Value for Test of Close Fit (RMSEA < 0.05) = 0.00
Expected Cross-Validation Index (ECVI) = 0.35
90 Percent Confidence Interval for ECVI = (0.27 ; 0.45)
ECVI for Saturated Model = 0.078
ECVI for Independence Model = 2.65
Chi-Square for Independence Model with 10 Degrees of Freedom = 1005.54
Independence AIC = 1015.54
Model AIC = 134.27
Saturated AIC = 30.00
Independence CAIC = 1040.29
Model CAIC = 183.78
Saturated CAIC = 104.26
Normed Fit Index (NFI) = 0.90
Non-Normed Fit Index (NNFI) = 0.80
Parsimony Normed Fit Index (PNFI) = 0.45
Comparative Fit Index (CFI) = 0.90
Incremental Fit Index (IFI) = 0.90
Relative Fit Index (RFI) = 0.80
Critical N (CN) = 57.30
Root Mean Square Residual (RMR) = 0.062
Standardized RMR = 0.062
Goodness of Fit Index (GFI) = 0.８
Adjusted Goodness of Fit Index (AGFI) = 0.68
Parsimony Goodness of Fit Index (PGFI) = 0.30
Modification Indices and Expected Change
No Non-Zero Modification Indices for LAMBDA-X
Modification Indices and Expected Change
--
※ 發信站: 批踢踢實業坊(ptt.cc)
◆ From: 140.128.118.210
推
05/04 15:30, , 1F
05/04 15:30, 1F
討論串 (同標題文章)
完整討論串 (本文為第 2 之 5 篇)：