Re: [問題] lisrel配適度分析問題

看板Statistics作者mld7558 (amy)時間13年前 (2012/05/04 16:07)推噓3(3推 0噓 4→)

留言7則, 2人參與討論串3/5 (看更多)

※ 引述《mld7558 (amy)》之銘言： ※ 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 THETA-DELTA 1 2 3 4 5 -------- -------- -------- -------- -------- 0.45 0.58 0.40 0.36 0.30 (0.04) (0.05) (0.04) (0.03) (0.03) 11.54 12.48 10.96 10.46 9.43 　　　　　　　　　　　　　 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 　No Non-Zero Modification Indices for PHI Modification Indices for THETA-DELTA 1 2 3 4 5 -------- -------- -------- -------- -------- 1 - - 2 64.82 - - 3 1.66 7.23 - - 4 9.64 25.70 4.21 - - 5 16.89 19.53 1.49 77.93 - - Expected Change for THETA-DELTA 1 2 3 4 5 -------- -------- -------- -------- -------- 1 - - 2 0.25 - - 3 0.04 0.08 - - 4 -0.09 -0.15 -0.06 - - 5 -0.12 -0.13 -0.04 0.27 - - Completely Standardized Expected Change for THETA-DELTA 1 2 3 4 5 -------- -------- -------- -------- -------- 1 - - 2 0.25 - - 3 0.04 0.08 - - 4 -0.09 -0.15 -0.06 - - 5 -0.12 -0.13 -0.04 0.27 - - Standardized Solution LAMBDA-X ATITUDE -------- 1 0.74 2 0.65 3 0.78 4 0.80 5 0.84 -- ※ 發信站: 批踢踢實業坊(ptt.cc) ◆ From: 140.128.118.210

推

sk2allwin

05/04 17:02, , 1^F

05/04 17:02, 1^F

→

sk2allwin

05/04 17:04, , 2^F

05/04 17:04, 2^F

→

mld7558

05/04 17:18, , 3^F

05/04 17:18, 3^F