健康測量問卷實作課程
維鈞組
2022-01-08
1.研究簡介
原目的：C肝全口服抗病毒藥物治療前後之生活品質比較(前後測)
改變目的：前後測合併，C肝病人一般生活品質與肝病相關生活品質的評估比較
2.個案簡介
前測:129
後測:111
Total:240
3.Data簡介
WHOQOL-BREF(共28題)
Overall-1
Overall-2
Physical: 3,4,10,15,16,17,18
Psychological: 5,6,7,11,19,26
Social: 20,21,22,27
Environment: 8,9,12,13,14,23,24,25,28
CLDQ(共29題)
Abdominal Symptom (AS): 1,5,17
Fatigue(FA): 2,4,8,11,13
Systemic Symptoms (SS): 3,6,21,23,27
Activity(AC): 7,9,14
Emotional Function(EF): 10,12,15,16,19,20,24,26
Worry(WO): 18,22,25,28,29
#read data
dta<-read.csv("D://HCVQ57n.csv", head=T, fileEncoding = "UTF-8-BOM")
str(dta)## 'data.frame': 240 obs. of 113 variables:
## $ SN : int 1 2 3 4 5 6 7 8 9 10 ...
## $ Res : int 1 1 1 1 1 1 1 1 1 1 ...
## $ Fitting : int 1 1 1 1 1 1 1 1 1 1 ...
## $ Chart : int 1694416 1209982 1694451 1698629 1694439 1694426 1699056 1694437 1694448 1698631 ...
## $ Attending : int 8 8 8 8 8 8 8 8 8 8 ...
## $ Hyperlipidemia: int 0 0 0 0 0 1 0 0 0 1 ...
## $ HTN : int 0 0 0 0 0 0 0 0 1 0 ...
## $ DM : int 0 0 0 0 0 0 0 0 0 1 ...
## $ CKD : int 0 0 0 1 0 0 0 0 0 0 ...
## $ HBV : int 0 0 0 0 0 0 0 0 0 0 ...
## $ CAD : int 0 0 0 0 0 0 0 0 0 0 ...
## $ HCC : int 0 0 0 0 0 0 0 0 0 0 ...
## $ Comorbid_Bi : int 0 0 0 1 0 1 0 0 1 1 ...
## $ Age_Group : int 5 1 4 4 5 4 2 5 2 5 ...
## $ Sex : int 1 2 1 2 2 2 1 1 2 1 ...
## $ Marriage : int 2 2 2 4 2 2 2 1 1 2 ...
## $ Education : int 2 5 2 2 1 2 2 3 3 2 ...
## $ Occupation : int 5 7 6 4 1 6 4 6 7 6 ...
## $ Income : int 1 2 1 2 1 1 3 1 1 1 ...
## $ Inc_Source : num 1 2 2 1 4 1 4 5 1 5 ...
## $ W_overall : int 4 4 3 3 4 4 4 4 3 3 ...
## $ W_general : int 4 3 3 3 4 4 4 2 3 2 ...
## $ W_phy : int 27 26 20 23 19 19 28 27 30 20 ...
## $ W_psy : int 25 19 17 20 23 24 24 22 22 23 ...
## $ W_soc : int 16 13 12 13 18 18 16 20 17 17 ...
## $ W_env : int 35 33 27 31 34 35 40 38 37 35 ...
## $ W01 : int 4 4 3 3 4 4 4 4 3 3 ...
## $ W02 : int 4 3 3 3 4 4 4 2 3 2 ...
## $ W03 : int 4 4 4 4 4 4 4 3 5 2 ...
## $ W04 : int 4 4 2 4 2 2 3 5 5 3 ...
## $ W05 : int 4 4 3 3 3 4 4 5 3 4 ...
## $ W06 : int 4 4 3 4 5 5 4 4 4 5 ...
## $ W07 : int 4 2 3 2 2 2 4 3 4 2 ...
## $ W08 : int 4 3 3 3 1 1 4 4 4 2 ...
## $ W09 : int 4 4 3 3 4 4 4 4 5 4 ...
## $ W10 : int 4 3 3 3 4 4 4 4 3 3 ...
## $ W11 : int 4 3 2 3 5 5 4 4 3 5 ...
## $ W12 : int 3 3 3 3 3 3 5 3 3 5 ...
## $ W13 : int 4 4 3 4 4 4 4 4 4 4 ...
## $ W14 : int 4 3 2 5 5 5 4 3 4 5 ...
## $ W15 : int 4 4 3 3 2 2 5 3 4 4 ...
## $ W16 : int 3 3 2 3 1 1 4 5 5 2 ...
## $ W17 : int 4 4 3 3 3 3 4 3 4 3 ...
## $ W18 : int 4 4 3 3 3 3 4 4 4 3 ...
## $ W19 : int 4 3 3 3 4 4 4 4 4 4 ...
## $ W20 : int 4 2 3 3 5 5 4 5 5 4 ...
## $ W21 : int 4 3 3 4 4 4 4 5 3 5 ...
## $ W22 : int 4 4 3 3 4 4 3 5 5 4 ...
## $ W23 : int 4 4 3 3 4 4 5 5 5 4 ...
## $ W24 : int 4 4 3 3 5 5 5 5 5 4 ...
## $ W25 : int 4 4 3 3 3 4 5 5 3 4 ...
## $ W26 : int 5 3 3 5 4 4 4 2 4 3 ...
## $ W27 : int 4 4 3 3 5 5 5 5 4 4 ...
## $ W28 : int 4 4 4 4 5 5 4 5 4 3 ...
## $ C_as : num 3.33 5.67 2.33 1.67 2 ...
## $ C_fa : num 3.4 4.2 4.4 3 2.4 2.4 1.2 3.8 2.4 4.8 ...
## $ C_ss : num 2.8 3.6 3.8 2.4 2.8 2.4 2.4 3.6 3 4 ...
## $ C_ac : num 2.67 3 2 3.33 2.33 ...
## $ C_ef : num 2.38 3.25 4 2 2.12 ...
## $ C_wo : num 1.17 0.8 1.2 3.4 3.8 ...
## $ C_avg : num 2.62 3.42 2.96 2.63 2.58 ...
## $ C01 : int 4 6 4 2 2 2 2 6 2 1 ...
## $ C02 : int 5 6 6 4 4 4 2 7 5 1 ...
## $ C03 : int 5 5 2 2 7 4 2 2 4 1 ...
## $ C04 : int 4 4 4 2 4 4 1 4 1 6 ...
## $ C05 : int 2 5 2 1 1 1 2 2 6 1 ...
## $ C06 : int 3 5 4 1 1 2 1 2 2 5 ...
## $ C07 : int 1 4 2 4 1 1 1 2 5 4 ...
## $ C08 : int 4 4 4 4 2 1 1 2 2 5 ...
## $ C09 : int 3 2 3 3 5 5 2 2 2 6 ...
## $ C10 : int 1 2 6 1 1 2 1 2 1 2 ...
## $ C11 : int 2 3 4 4 1 2 1 2 2 6 ...
## $ C12 : int 1 4 4 1 1 1 1 2 6 2 ...
## $ C13 : int 2 4 4 1 1 1 1 4 2 6 ...
## $ C14 : int 4 3 1 3 1 1 1 2 1 4 ...
## $ C15 : int 3 2 2 1 2 2 1 2 2 2 ...
## $ C16 : int 4 5 4 4 2 6 7 2 1 6 ...
## $ C17 : int 4 6 1 2 3 1 2 2 6 1 ...
## $ C18 : int 2 1 3 4 7 7 1 2 1 7 ...
## $ C19 : int 3 1 3 2 4 1 1 2 2 3 ...
## $ C20 : int 1 6 2 2 2 7 7 1 1 6 ...
## $ C21 : int 2 1 3 2 2 2 1 1 1 6 ...
## $ C22 : int 1 1 1 4 7 6 1 7 1 2 ...
## $ C23 : int 2 4 6 2 3 3 1 7 7 1 ...
## $ C24 : int 4 1 5 1 2 2 1 1 1 2 ...
## $ C25 : int 2 1 2 5 7 7 1 1 1 2 ...
## $ C26 : int 2 5 6 4 3 3 1 2 3 5 ...
## $ C27 : int 2 3 4 5 1 1 7 6 1 7 ...
## $ C28 : int 1 1 1 5 4 4 1 1 1 2 ...
## $ C29 : int 1 1 1 4 1 7 1 3 1 2 ...
## $ Age : num 72.8 32.7 67.5 65.7 70.2 ...
## $ Mx : int 10 7 10 13 10 10 12 10 10 12 ...
## $ MX_Brief : int 6 5 6 7 6 6 7 6 6 7 ...
## $ IFN_Exp : int 0 0 0 0 0 0 0 0 0 0 ...
## $ GT : int 6 1 2 2 2 6 2 2 2 2 ...
## $ Fibrosis : int 0 0 2 4 1 1 0 2 0 2 ...
## $ X1.HCVRNA : int 2170000 196000 4790 16800 2330000 44900 47400 559000 1760000 16800 ...
## $ X1.WBC : int 5650 4140 2620 3600 5720 3680 4700 5770 3840 6100 ...
## $ X1.Hb : num 11.9 13.7 13.8 10.1 14.6 12.4 10 13.4 14.7 11.7 ...
## [list output truncated]head(dta)## SN Res Fitting Chart Attending Hyperlipidemia HTN DM CKD HBV CAD HCC
## 1 1 1 1 1694416 8 0 0 0 0 0 0 0
## 2 2 1 1 1209982 8 0 0 0 0 0 0 0
## 3 3 1 1 1694451 8 0 0 0 0 0 0 0
## 4 4 1 1 1698629 8 0 0 0 1 0 0 0
## 5 5 1 1 1694439 8 0 0 0 0 0 0 0
## 6 6 1 1 1694426 8 1 0 0 0 0 0 0
## Comorbid_Bi Age_Group Sex Marriage Education Occupation Income Inc_Source
## 1 0 5 1 2 2 5 1 1
## 2 0 1 2 2 5 7 2 2
## 3 0 4 1 2 2 6 1 2
## 4 1 4 2 4 2 4 2 1
## 5 0 5 2 2 1 1 1 4
## 6 1 4 2 2 2 6 1 1
## W_overall W_general W_phy W_psy W_soc W_env W01 W02 W03 W04 W05 W06 W07 W08
## 1 4 4 27 25 16 35 4 4 4 4 4 4 4 4
## 2 4 3 26 19 13 33 4 3 4 4 4 4 2 3
## 3 3 3 20 17 12 27 3 3 4 2 3 3 3 3
## 4 3 3 23 20 13 31 3 3 4 4 3 4 2 3
## 5 4 4 19 23 18 34 4 4 4 2 3 5 2 1
## 6 4 4 19 24 18 35 4 4 4 2 4 5 2 1
## W09 W10 W11 W12 W13 W14 W15 W16 W17 W18 W19 W20 W21 W22 W23 W24 W25 W26 W27
## 1 4 4 4 3 4 4 4 3 4 4 4 4 4 4 4 4 4 5 4
## 2 4 3 3 3 4 3 4 3 4 4 3 2 3 4 4 4 4 3 4
## 3 3 3 2 3 3 2 3 2 3 3 3 3 3 3 3 3 3 3 3
## 4 3 3 3 3 4 5 3 3 3 3 3 3 4 3 3 3 3 5 3
## 5 4 4 5 3 4 5 2 1 3 3 4 5 4 4 4 5 3 4 5
## 6 4 4 5 3 4 5 2 1 3 3 4 5 4 4 4 5 4 4 5
## W28 C_as C_fa C_ss C_ac C_ef C_wo C_avg C01 C02 C03 C04 C05
## 1 4 3.333333 3.4 2.8 2.666667 2.375 1.166667 2.623611 4 5 5 4 2
## 2 4 5.666667 4.2 3.6 3.000000 3.250 0.800000 3.419444 6 6 5 4 5
## 3 4 2.333333 4.4 3.8 2.000000 4.000 1.200000 2.955556 4 6 2 4 2
## 4 4 1.666667 3.0 2.4 3.333333 2.000 3.400000 2.633333 2 4 2 2 1
## 5 5 2.000000 2.4 2.8 2.333333 2.125 3.800000 2.576389 2 4 7 4 1
## 6 5 1.333333 2.4 2.4 2.333333 3.000 4.800000 2.711111 2 4 4 4 1
## C06 C07 C08 C09 C10 C11 C12 C13 C14 C15 C16 C17 C18 C19 C20 C21 C22 C23 C24
## 1 3 1 4 3 1 2 1 2 4 3 4 4 2 3 1 2 1 2 4
## 2 5 4 4 2 2 3 4 4 3 2 5 6 1 1 6 1 1 4 1
## 3 4 2 4 3 6 4 4 4 1 2 4 1 3 3 2 3 1 6 5
## 4 1 4 4 3 1 4 1 1 3 1 4 2 4 2 2 2 4 2 1
## 5 1 1 2 5 1 1 1 1 1 2 2 3 7 4 2 2 7 3 2
## 6 2 1 1 5 2 2 1 1 1 2 6 1 7 1 7 2 6 3 2
## C25 C26 C27 C28 C29 Age Mx MX_Brief IFN_Exp GT Fibrosis X1.HCVRNA X1.WBC
## 1 2 2 2 1 1 72.84932 10 6 0 6 0 2170000 5650
## 2 1 5 3 1 1 32.71233 7 5 0 1 0 196000 4140
## 3 2 6 4 1 1 67.53973 10 6 0 2 2 4790 2620
## 4 5 4 5 5 4 65.73151 13 7 0 2 4 16800 3600
## 5 7 3 1 4 1 70.16986 10 6 0 2 1 2330000 5720
## 6 7 3 1 4 7 70.27123 10 6 0 6 1 44900 3680
## X1.Hb X1.Platelet X1.INR X1.Albumin X1.GOT X1.GPT X1.Tbil X1.Dbil X1..AFP
## 1 11.9 324 1.01 4.0 29 30 0.72 0.23 1.89
## 2 13.7 234 0.98 4.4 24 25 0.64 0.16 1.83
## 3 13.8 162 1.02 4.3 23 17 0.56 0.18 1.48
## 4 10.1 88 1.04 4.1 81 69 0.40 0.20 4.74
## 5 14.6 204 0.95 3.7 24 20 0.78 0.25 1.71
## 6 12.4 183 0.93 3.9 29 29 0.42 0.11 3.10
## X1.BUN X1.Cr X1.HBsAg_Bi X1.Decom SVR12_Status SVR12_ITT
## 1 14.4 0.9 1 0 2 1
## 2 14.3 0.5 1 0 2 1
## 3 13.7 0.9 1 0 2 1
## 4 66.0 4.3 1 0 2 1
## 5 19.6 0.6 1 0 2 1
## 6 19.2 1.0 1 0 2 1names(dta)## [1] "SN" "Res" "Fitting" "Chart"
## [5] "Attending" "Hyperlipidemia" "HTN" "DM"
## [9] "CKD" "HBV" "CAD" "HCC"
## [13] "Comorbid_Bi" "Age_Group" "Sex" "Marriage"
## [17] "Education" "Occupation" "Income" "Inc_Source"
## [21] "W_overall" "W_general" "W_phy" "W_psy"
## [25] "W_soc" "W_env" "W01" "W02"
## [29] "W03" "W04" "W05" "W06"
## [33] "W07" "W08" "W09" "W10"
## [37] "W11" "W12" "W13" "W14"
## [41] "W15" "W16" "W17" "W18"
## [45] "W19" "W20" "W21" "W22"
## [49] "W23" "W24" "W25" "W26"
## [53] "W27" "W28" "C_as" "C_fa"
## [57] "C_ss" "C_ac" "C_ef" "C_wo"
## [61] "C_avg" "C01" "C02" "C03"
## [65] "C04" "C05" "C06" "C07"
## [69] "C08" "C09" "C10" "C11"
## [73] "C12" "C13" "C14" "C15"
## [77] "C16" "C17" "C18" "C19"
## [81] "C20" "C21" "C22" "C23"
## [85] "C24" "C25" "C26" "C27"
## [89] "C28" "C29" "Age" "Mx"
## [93] "MX_Brief" "IFN_Exp" "GT" "Fibrosis"
## [97] "X1.HCVRNA" "X1.WBC" "X1.Hb" "X1.Platelet"
## [101] "X1.INR" "X1.Albumin" "X1.GOT" "X1.GPT"
## [105] "X1.Tbil" "X1.Dbil" "X1..AFP" "X1.BUN"
## [109] "X1.Cr" "X1.HBsAg_Bi" "X1.Decom" "SVR12_Status"
## [113] "SVR12_ITT"4.WHOQOL-BREF內在一致性
Conbarch’s alpha
library(psych)
#算資料的內在一致性，算Conbarch's alpha(WHOQOL-BREF在資料的27~54column)
#指令alpha(資料名[row,column])
#這邊row空著(所有row的資料都納入)
#column依要分析的資料修改，這邊是第27到第54個column
#Conbarch's alpha算出來的存成dta_1
dta_1<-alpha(dta[,27:54])
summary(dta_1) ##
## Reliability analysis
## raw_alpha std.alpha G6(smc) average_r S/N ase mean sd median_r
## 0.9 0.9 0.93 0.25 9.5 0.0093 3.4 0.46 0.24Conbarch’s alpha結論
看std.alpha值 std.alpha=0.905(0.8以上就可以接受)
#列出Conbarch's alpha所有資料
dta_1##
## Reliability analysis
## Call: alpha(x = dta[, 27:54])
##
## raw_alpha std.alpha G6(smc) average_r S/N ase mean sd median_r
## 0.9 0.9 0.93 0.25 9.5 0.0093 3.4 0.46 0.24
##
## lower alpha upper 95% confidence boundaries
## 0.88 0.9 0.92
##
## Reliability if an item is dropped:
## raw_alpha std.alpha G6(smc) average_r S/N alpha se var.r med.r
## W01 0.90 0.90 0.92 0.25 9.1 0.0097 0.012 0.25
## W02 0.90 0.90 0.92 0.26 9.4 0.0094 0.012 0.25
## W03 0.90 0.91 0.93 0.26 9.6 0.0092 0.011 0.25
## W04 0.90 0.90 0.93 0.26 9.3 0.0093 0.012 0.25
## W05 0.90 0.90 0.92 0.25 9.1 0.0097 0.012 0.24
## W06 0.89 0.90 0.92 0.25 8.9 0.0099 0.012 0.24
## W07 0.90 0.90 0.92 0.25 9.2 0.0096 0.012 0.24
## W08 0.90 0.90 0.92 0.26 9.2 0.0096 0.012 0.25
## W09 0.90 0.90 0.92 0.26 9.4 0.0094 0.011 0.25
## W10 0.89 0.90 0.92 0.25 9.0 0.0098 0.012 0.24
## W11 0.90 0.90 0.92 0.25 9.2 0.0096 0.012 0.24
## W12 0.89 0.90 0.92 0.25 9.0 0.0098 0.012 0.24
## W13 0.89 0.90 0.92 0.25 9.0 0.0098 0.012 0.24
## W14 0.90 0.90 0.92 0.25 9.2 0.0095 0.012 0.25
## W15 0.89 0.90 0.92 0.25 9.0 0.0098 0.012 0.24
## W16 0.90 0.90 0.92 0.25 9.2 0.0096 0.012 0.25
## W17 0.89 0.90 0.92 0.25 8.9 0.0099 0.011 0.24
## W18 0.89 0.90 0.92 0.24 8.7 0.0100 0.011 0.23
## W19 0.89 0.90 0.92 0.25 8.8 0.0099 0.011 0.24
## W20 0.89 0.90 0.92 0.25 9.0 0.0097 0.012 0.24
## W21 0.90 0.90 0.92 0.25 9.1 0.0097 0.012 0.24
## W22 0.90 0.90 0.92 0.25 9.2 0.0096 0.012 0.25
## W23 0.89 0.90 0.92 0.25 8.9 0.0098 0.012 0.24
## W24 0.90 0.90 0.92 0.26 9.3 0.0095 0.012 0.25
## W25 0.90 0.90 0.92 0.26 9.3 0.0095 0.012 0.25
## W26 0.90 0.90 0.93 0.26 9.3 0.0095 0.012 0.25
## W27 0.90 0.90 0.92 0.25 9.1 0.0097 0.012 0.24
## W28 0.90 0.90 0.92 0.25 9.2 0.0096 0.013 0.24
##
## Item statistics
## n raw.r std.r r.cor r.drop mean sd
## W01 240 0.54 0.55 0.53 0.50 3.3 0.74
## W02 240 0.42 0.41 0.38 0.36 3.0 0.92
## W03 240 0.32 0.31 0.27 0.25 3.8 1.04
## W04 240 0.45 0.43 0.40 0.37 3.5 1.20
## W05 240 0.55 0.54 0.53 0.49 3.0 1.01
## W06 240 0.63 0.64 0.63 0.59 3.3 0.92
## W07 240 0.52 0.51 0.49 0.46 3.0 0.92
## W08 240 0.47 0.47 0.45 0.42 3.5 0.83
## W09 240 0.37 0.38 0.35 0.31 3.4 0.90
## W10 240 0.60 0.60 0.58 0.56 3.2 0.84
## W11 240 0.49 0.50 0.47 0.44 3.5 0.79
## W12 240 0.60 0.60 0.58 0.55 3.1 1.00
## W13 240 0.60 0.60 0.59 0.55 3.5 0.85
## W14 240 0.49 0.48 0.45 0.43 3.1 1.05
## W15 240 0.59 0.57 0.56 0.54 3.4 1.00
## W16 240 0.50 0.49 0.47 0.43 3.0 1.02
## W17 240 0.65 0.65 0.65 0.62 3.4 0.74
## W18 240 0.72 0.73 0.73 0.69 3.4 0.77
## W19 240 0.66 0.67 0.67 0.63 3.5 0.76
## W20 240 0.58 0.59 0.58 0.53 3.4 0.79
## W21 240 0.52 0.53 0.51 0.47 3.0 0.83
## W22 240 0.50 0.51 0.49 0.44 3.4 0.86
## W23 240 0.61 0.62 0.62 0.57 3.6 0.76
## W24 240 0.42 0.44 0.41 0.37 3.9 0.73
## W25 240 0.46 0.47 0.44 0.41 3.7 0.78
## W26 240 0.45 0.44 0.41 0.39 3.5 0.99
## W27 240 0.54 0.56 0.53 0.50 3.4 0.74
## W28 240 0.52 0.52 0.49 0.47 3.8 0.81
##
## Non missing response frequency for each item
## 1 2 3 4 5 6 miss
## W01 0.01 0.09 0.50 0.35 0.05 0 0
## W02 0.04 0.28 0.41 0.23 0.05 0 0
## W03 0.01 0.12 0.25 0.33 0.28 0 0
## W04 0.03 0.22 0.25 0.22 0.27 0 0
## W05 0.12 0.12 0.48 0.24 0.04 0 0
## W06 0.05 0.08 0.42 0.37 0.07 0 0
## W07 0.07 0.17 0.47 0.26 0.03 0 0
## W08 0.04 0.06 0.35 0.50 0.05 0 0
## W09 0.04 0.09 0.32 0.49 0.06 0 0
## W10 0.02 0.16 0.45 0.33 0.05 0 0
## W11 0.02 0.05 0.44 0.40 0.09 0 0
## W12 0.08 0.14 0.43 0.28 0.07 0 0
## W13 0.02 0.09 0.38 0.42 0.10 0 0
## W14 0.07 0.26 0.27 0.35 0.05 0 0
## W15 0.05 0.13 0.26 0.47 0.09 0 0
## W16 0.07 0.27 0.33 0.28 0.05 0 0
## W17 0.02 0.07 0.46 0.42 0.04 0 0
## W18 0.01 0.10 0.46 0.38 0.05 0 0
## W19 0.01 0.07 0.41 0.45 0.06 0 0
## W20 0.01 0.07 0.44 0.40 0.07 0 0
## W21 0.06 0.10 0.63 0.16 0.04 0 0
## W22 0.04 0.07 0.45 0.38 0.06 0 0
## W23 0.01 0.06 0.30 0.55 0.07 0 0
## W24 0.00 0.03 0.24 0.55 0.17 0 0
## W25 0.01 0.05 0.28 0.53 0.13 0 0
## W26 0.02 0.14 0.33 0.34 0.17 0 0
## W27 0.00 0.06 0.50 0.36 0.07 0 0
## W28 0.00 0.07 0.21 0.56 0.16 0 0Conbarch’s alpha各資料
Reliability if an item is dropped→W03，std.alpha會變成0.906，略高於overall的0.905 Item statistics→W03的r.cor=0.270→發現W03與其他題的相關性最低 真的要刪題，或許可以考慮W03。但WHOQOL-BREF應用度已經很廣泛，刪掉此題與其他研究的可比性會降低… Conbarch’s alpha被詬病的是每題的貢獻度一樣，有可能被低估 可以改作Mcdonald’s omega assumptions (內在一致性結果會比較高) 文章發表Conbarch’s alpha還是占一席之地，原因是：大家比較習慣的用法、和其他問卷的COnbarch’s alpha有可比性。
Mcdonald’s omega
#需要加裝package{GPArotation}
library(GPArotation)
#指令改成omega
dta_2<-omega(dta[,27:54])
summary(dta_2)## Omega
## omega(m = dta[, 27:54])
## Alpha: 0.9
## G.6: 0.93
## Omega Hierarchical: 0.59
## Omega H asymptotic: 0.64
## Omega Total 0.92
##
## With eigenvalues of:
## g F1* F2* F3*
## 4.8 2.5 1.1 1.2
## The degrees of freedom for the model is 297 and the fit was 2.8
## The number of observations was 240 with Chi Square = 634.13 with prob < 0
##
## The root mean square of the residuals is 0.06
## The df corrected root mean square of the residuals is 0.07
##
## RMSEA and the 0.9 confidence intervals are 0.069 0.062 0.076
## BIC = -993.62Explained Common Variance of the general factor = 0.5
##
## Total, General and Subset omega for each subset
## g F1* F2* F3*
## Omega total for total scores and subscales 0.92 0.86 0.63 0.74
## Omega general for total scores and subscales 0.59 0.49 0.33 0.42
## Omega group for total scores and subscales 0.18 0.37 0.29 0.32Omega 結論
看Omega Total=0.92 略高於Conbrach’s alpha
5.CLDQ內在一致性
Conbarch’s alpha
#算資料的內在一致性，算Conbarch's alpha(CLDQ在資料的62~90column)
dta_3<-alpha(dta[,62:90])
summary(dta_3)##
## Reliability analysis
## raw_alpha std.alpha G6(smc) average_r S/N ase mean sd median_r
## 0.92 0.93 0.95 0.3 13 0.0073 2.3 0.83 0.3Conbarch’s alpha結論
看std.alpha值 std.alpha=0.927(0.8以上就可以接受)
#列出Conbarch's alpha所有資料
dta_3##
## Reliability analysis
## Call: alpha(x = dta[, 62:90])
##
## raw_alpha std.alpha G6(smc) average_r S/N ase mean sd median_r
## 0.92 0.93 0.95 0.3 13 0.0073 2.3 0.83 0.3
##
## lower alpha upper 95% confidence boundaries
## 0.91 0.92 0.94
##
## Reliability if an item is dropped:
## raw_alpha std.alpha G6(smc) average_r S/N alpha se var.r med.r
## C01 0.92 0.92 0.95 0.30 12 0.0076 0.016 0.30
## C02 0.92 0.92 0.95 0.30 12 0.0076 0.016 0.30
## C03 0.92 0.92 0.95 0.30 12 0.0077 0.016 0.29
## C04 0.92 0.92 0.95 0.30 12 0.0076 0.016 0.30
## C05 0.92 0.92 0.95 0.30 12 0.0076 0.016 0.30
## C06 0.92 0.92 0.95 0.30 12 0.0077 0.017 0.29
## C07 0.92 0.93 0.95 0.31 12 0.0075 0.016 0.30
## C08 0.92 0.92 0.95 0.30 12 0.0076 0.016 0.30
## C09 0.92 0.93 0.95 0.31 12 0.0075 0.017 0.30
## C10 0.92 0.92 0.95 0.30 12 0.0077 0.016 0.29
## C11 0.92 0.92 0.95 0.30 12 0.0078 0.016 0.29
## C12 0.92 0.92 0.95 0.30 12 0.0078 0.016 0.29
## C13 0.92 0.92 0.95 0.30 12 0.0076 0.016 0.30
## C14 0.92 0.92 0.95 0.30 12 0.0076 0.017 0.30
## C15 0.92 0.92 0.95 0.30 12 0.0078 0.015 0.29
## C16 0.92 0.93 0.95 0.31 12 0.0075 0.016 0.30
## C17 0.92 0.92 0.95 0.30 12 0.0076 0.016 0.30
## C18 0.92 0.92 0.95 0.30 12 0.0076 0.016 0.30
## C19 0.92 0.92 0.95 0.30 12 0.0078 0.015 0.29
## C20 0.92 0.93 0.95 0.31 12 0.0074 0.016 0.30
## C21 0.92 0.93 0.95 0.31 12 0.0075 0.017 0.30
## C22 0.92 0.92 0.95 0.30 12 0.0076 0.016 0.30
## C23 0.92 0.93 0.95 0.31 12 0.0074 0.016 0.30
## C24 0.92 0.92 0.95 0.30 12 0.0078 0.015 0.29
## C25 0.92 0.92 0.95 0.30 12 0.0077 0.015 0.30
## C26 0.92 0.92 0.95 0.30 12 0.0077 0.016 0.29
## C27 0.92 0.93 0.95 0.31 13 0.0073 0.016 0.30
## C28 0.92 0.92 0.95 0.30 12 0.0077 0.016 0.30
## C29 0.92 0.93 0.95 0.32 13 0.0071 0.014 0.31
##
## Item statistics
## n raw.r std.r r.cor r.drop mean sd
## C01 240 0.56 0.58 0.56 0.52 2.0 1.4
## C02 240 0.54 0.55 0.53 0.49 2.6 1.6
## C03 240 0.62 0.62 0.60 0.57 2.4 1.6
## C04 240 0.57 0.57 0.55 0.53 2.7 1.5
## C05 240 0.55 0.57 0.56 0.52 1.7 1.1
## C06 240 0.60 0.61 0.59 0.57 2.2 1.4
## C07 240 0.47 0.48 0.46 0.43 2.1 1.3
## C08 240 0.57 0.57 0.55 0.53 2.7 1.5
## C09 240 0.50 0.49 0.47 0.45 2.8 1.6
## C10 240 0.64 0.65 0.64 0.61 2.2 1.4
## C11 240 0.69 0.69 0.69 0.66 2.5 1.4
## C12 240 0.68 0.69 0.68 0.65 2.0 1.4
## C13 240 0.58 0.58 0.56 0.54 2.1 1.3
## C14 240 0.53 0.54 0.51 0.49 1.8 1.4
## C15 240 0.73 0.74 0.74 0.70 2.0 1.2
## C16 240 0.53 0.50 0.50 0.47 3.0 1.9
## C17 240 0.61 0.63 0.62 0.58 1.8 1.2
## C18 240 0.56 0.56 0.54 0.51 2.1 1.6
## C19 240 0.73 0.74 0.74 0.70 1.9 1.2
## C20 240 0.50 0.48 0.47 0.44 2.5 1.8
## C21 240 0.49 0.48 0.45 0.43 2.7 1.7
## C22 240 0.56 0.56 0.55 0.52 2.0 1.5
## C23 240 0.48 0.48 0.44 0.42 2.8 1.7
## C24 240 0.73 0.73 0.73 0.70 2.0 1.3
## C25 240 0.62 0.62 0.63 0.58 2.0 1.5
## C26 240 0.64 0.64 0.63 0.60 2.2 1.4
## C27 240 0.39 0.37 0.34 0.33 2.6 1.8
## C28 240 0.60 0.61 0.60 0.57 1.9 1.3
## C29 240 0.28 0.27 0.23 0.21 1.9 1.7
##
## Non missing response frequency for each item
## 1 2 3 4 5 6 7 miss
## C01 0.50 0.22 0.11 0.12 0.02 0.02 0.01 0
## C02 0.33 0.25 0.13 0.15 0.08 0.03 0.03 0
## C03 0.39 0.25 0.11 0.12 0.07 0.05 0.01 0
## C04 0.28 0.23 0.19 0.20 0.04 0.05 0.01 0
## C05 0.61 0.22 0.10 0.04 0.02 0.01 0.00 0
## C06 0.43 0.25 0.12 0.12 0.05 0.02 0.00 0
## C07 0.48 0.25 0.09 0.12 0.03 0.02 0.00 0
## C08 0.29 0.24 0.19 0.15 0.08 0.04 0.02 0
## C09 0.26 0.29 0.15 0.13 0.08 0.05 0.03 0
## C10 0.41 0.26 0.15 0.10 0.05 0.03 0.01 0
## C11 0.32 0.29 0.16 0.12 0.08 0.03 0.01 0
## C12 0.48 0.27 0.10 0.09 0.03 0.03 0.01 0
## C13 0.44 0.29 0.12 0.10 0.03 0.03 0.01 0
## C14 0.59 0.21 0.07 0.06 0.04 0.02 0.01 0
## C15 0.43 0.31 0.12 0.10 0.03 0.01 0.00 0
## C16 0.27 0.25 0.08 0.15 0.12 0.09 0.04 0
## C17 0.57 0.21 0.09 0.08 0.03 0.01 0.00 0
## C18 0.51 0.22 0.10 0.07 0.05 0.03 0.03 0
## C19 0.48 0.30 0.10 0.09 0.03 0.00 0.01 0
## C20 0.40 0.24 0.08 0.08 0.10 0.07 0.03 0
## C21 0.33 0.20 0.13 0.16 0.10 0.05 0.02 0
## C22 0.52 0.23 0.10 0.06 0.04 0.04 0.01 0
## C23 0.30 0.24 0.14 0.16 0.06 0.06 0.04 0
## C24 0.50 0.24 0.12 0.10 0.02 0.03 0.00 0
## C25 0.55 0.22 0.08 0.06 0.04 0.03 0.02 0
## C26 0.39 0.29 0.16 0.09 0.04 0.03 0.01 0
## C27 0.39 0.21 0.12 0.12 0.07 0.03 0.06 0
## C28 0.53 0.25 0.11 0.05 0.03 0.02 0.01 0
## C29 0.65 0.19 0.03 0.03 0.02 0.00 0.07 0Conbarch’s alpha各資料
Reliability if an item is dropped→C29，std.alpha會變成0.928，略高於overall的0.927 Item statistics→C29的r.cor=0.230→發現C29與其他題的相關性最低 真的要刪題，或許可以考慮C29。但刪題後面臨的問題跟前面的WHOQOL-BREF一樣
Mcdonald’s omega
#指令改成omega
dta_4<-omega(dta[,62:90])
summary(dta_4)## Omega
## omega(m = dta[, 62:90])
## Alpha: 0.93
## G.6: 0.95
## Omega Hierarchical: 0.64
## Omega H asymptotic: 0.68
## Omega Total 0.94
##
## With eigenvalues of:
## g F1* F2* F3*
## 6.4 2.7 1.5 1.5
## The degrees of freedom for the model is 322 and the fit was 4.37
## The number of observations was 240 with Chi Square = 989.92 with prob < 0
##
## The root mean square of the residuals is 0.06
## The df corrected root mean square of the residuals is 0.07
##
## RMSEA and the 0.9 confidence intervals are 0.093 0.087 0.1
## BIC = -774.85Explained Common Variance of the general factor = 0.52
##
## Total, General and Subset omega for each subset
## g F1* F2* F3*
## Omega total for total scores and subscales 0.94 0.89 0.84 0.67
## Omega general for total scores and subscales 0.64 0.55 0.47 0.30
## Omega group for total scores and subscales 0.20 0.34 0.37 0.37Omega 結論
看Omega Total=0.94 略高於Conbrach’s alpha
6.WHOQOL平行分析
傳統EPA的方式，會計算出eigenvalues，>1要留，但因切點設1，有時容易有爭議
Parallel Analysis會有simulated data(模擬資料)：幫忙算要留幾個factor，通常當factor掉到小於simulated data時，就會不選，決定factor的數目用!比只看EPA eigenvalues似乎更客觀些
PCA→component：問卷中每個題目裡面都有屬於每一個factor，只是比例不同
FA=EFA→component：問卷中每個題目都分別”只”屬於一個factor，Parallel Analysis用模擬資料來做比較，得到的結果是「建議分成幾個factor」
PCA中的主成分是原始變量的線性組合，而EFA中的原始變量是公共因子的線性組合，因子是影響變量的潛在變量，變量中不能被因子所解釋的部分稱為誤差，因子和誤差均不能直接觀察到。(參考原文網址：https://kknews.cc/news/y8rgnvb.html)
#fa.parallel是parallel analysis的指令
#資料選第29~54 column (排除單題*2)
dta_5<-fa.parallel(dta[,29:54])
## Parallel analysis suggests that the number of factors = 5 and the number of components = 3Parallel analysis結論
PCA:the number of components = 3 (x的線) FA:number of factors = 5 (△的線) 因為FA的第6和第7個點就在紅線左右，所以有時會因simulation的資料選的不一樣，造成factors=6或factors7
#factor analysis當因素>=2時，會有轉軸的問題
#rotate要設，讓factor更清楚落在哪個象限
#nfactors="多少"，來自於fa.parallel的結果
#rotate="oblimin"斜交轉軸、="varimax"為正交轉軸
dta_6<-fa(dta[,29:54], nfactors=5, rotate = "oblimin")
dta_6## Factor Analysis using method = minres
## Call: fa(r = dta[, 29:54], nfactors = 5, rotate = "oblimin")
## Standardized loadings (pattern matrix) based upon correlation matrix
## MR2 MR1 MR4 MR3 MR5 h2 u2 com
## W03 0.15 0.25 0.23 -0.03 -0.44 0.29 0.71 2.5
## W04 0.18 0.28 0.25 -0.07 -0.21 0.25 0.75 3.8
## W05 0.08 0.18 0.06 0.15 0.44 0.40 0.60 1.7
## W06 0.16 0.18 0.18 0.13 0.39 0.47 0.53 2.6
## W07 -0.03 0.42 0.09 0.26 -0.02 0.32 0.68 1.8
## W08 -0.01 0.27 0.06 0.37 -0.01 0.28 0.72 1.9
## W09 -0.08 0.00 -0.02 0.74 0.04 0.52 0.48 1.0
## W10 -0.09 0.36 0.28 0.22 0.10 0.42 0.58 3.0
## W11 0.13 0.43 -0.10 0.19 0.04 0.29 0.71 1.7
## W12 0.04 0.41 0.02 0.16 0.31 0.44 0.56 2.2
## W13 0.36 0.51 -0.14 0.04 0.08 0.49 0.51 2.1
## W14 0.16 0.35 0.02 -0.03 0.16 0.26 0.74 1.9
## W15 -0.07 0.72 0.12 -0.03 0.00 0.56 0.44 1.1
## W16 -0.04 -0.11 0.77 0.11 -0.07 0.56 0.44 1.1
## W17 -0.01 0.37 0.52 -0.07 0.11 0.60 0.40 2.0
## W18 0.21 0.28 0.49 -0.01 0.06 0.62 0.38 2.1
## W19 0.16 0.15 0.44 0.05 0.22 0.51 0.49 2.1
## W20 0.68 0.06 0.02 -0.07 0.17 0.57 0.43 1.2
## W21 0.27 -0.05 0.34 -0.06 0.34 0.40 0.60 3.0
## W22 0.55 0.06 0.04 -0.07 0.16 0.40 0.60 1.2
## W23 0.34 -0.08 0.17 0.53 0.04 0.60 0.40 2.0
## W24 0.68 -0.12 0.03 0.11 -0.15 0.46 0.54 1.2
## W25 0.54 0.05 0.01 0.14 -0.16 0.35 0.65 1.3
## W26 0.08 0.27 -0.02 0.34 -0.11 0.24 0.76 2.3
## W27 0.36 0.08 0.04 0.14 0.24 0.35 0.65 2.2
## W28 0.20 0.15 0.20 0.22 -0.11 0.27 0.73 4.3
##
## MR2 MR1 MR4 MR3 MR5
## SS loadings 2.71 2.86 2.30 1.72 1.34
## Proportion Var 0.10 0.11 0.09 0.07 0.05
## Cumulative Var 0.10 0.21 0.30 0.37 0.42
## Proportion Explained 0.25 0.26 0.21 0.16 0.12
## Cumulative Proportion 0.25 0.51 0.72 0.88 1.00
##
## With factor correlations of
## MR2 MR1 MR4 MR3 MR5
## MR2 1.00 0.34 0.36 0.30 0.26
## MR1 0.34 1.00 0.44 0.22 0.32
## MR4 0.36 0.44 1.00 0.30 0.17
## MR3 0.30 0.22 0.30 1.00 0.12
## MR5 0.26 0.32 0.17 0.12 1.00
##
## Mean item complexity = 2
## Test of the hypothesis that 5 factors are sufficient.
##
## The degrees of freedom for the null model are 325 and the objective function was 9.59 with Chi Square of 2200.14
## The degrees of freedom for the model are 205 and the objective function was 1.56
##
## The root mean square of the residuals (RMSR) is 0.04
## The df corrected root mean square of the residuals is 0.05
##
## The harmonic number of observations is 240 with the empirical chi square 253.42 with prob < 0.012
## The total number of observations was 240 with Likelihood Chi Square = 352.31 with prob < 7e-10
##
## Tucker Lewis Index of factoring reliability = 0.873
## RMSEA index = 0.055 and the 90 % confidence intervals are 0.045 0.064
## BIC = -771.22
## Fit based upon off diagonal values = 0.98
## Measures of factor score adequacy
## MR2 MR1 MR4 MR3 MR5
## Correlation of (regression) scores with factors 0.90 0.90 0.89 0.86 0.81
## Multiple R square of scores with factors 0.81 0.81 0.80 0.74 0.66
## Minimum correlation of possible factor scores 0.63 0.62 0.60 0.47 0.31summary(dta_6)##
## Factor analysis with Call: fa(r = dta[, 29:54], nfactors = 5, rotate = "oblimin")
##
## Test of the hypothesis that 5 factors are sufficient.
## The degrees of freedom for the model is 205 and the objective function was 1.56
## The number of observations was 240 with Chi Square = 352.31 with prob < 7e-10
##
## The root mean square of the residuals (RMSA) is 0.04
## The df corrected root mean square of the residuals is 0.05
##
## Tucker Lewis Index of factoring reliability = 0.873
## RMSEA index = 0.055 and the 10 % confidence intervals are 0.045 0.064
## BIC = -771.22
## With factor correlations of
## MR2 MR1 MR4 MR3 MR5
## MR2 1.00 0.34 0.36 0.30 0.26
## MR1 0.34 1.00 0.44 0.22 0.32
## MR4 0.36 0.44 1.00 0.30 0.17
## MR3 0.30 0.22 0.30 1.00 0.12
## MR5 0.26 0.32 0.17 0.12 1.00斜交轉軸會有correlation
factoe correlation通常>0.8，會受到質疑
#以正交轉軸再做一次
dta_7<-fa(dta[,29:54], nfactors=5, rotate = "varimax")
dta_7## Factor Analysis using method = minres
## Call: fa(r = dta[, 29:54], nfactors = 5, rotate = "varimax")
## Standardized loadings (pattern matrix) based upon correlation matrix
## MR1 MR2 MR5 MR3 MR4 h2 u2 com
## W03 0.03 0.08 0.08 0.07 0.52 0.29 0.71 1.1
## W04 0.20 0.15 0.17 0.03 0.39 0.25 0.75 2.4
## W05 0.48 0.22 0.23 0.17 -0.19 0.40 0.60 2.6
## W06 0.48 0.30 0.33 0.19 -0.09 0.47 0.53 3.0
## W07 0.40 0.04 0.13 0.32 0.21 0.32 0.68 2.7
## W08 0.28 0.07 0.11 0.41 0.13 0.28 0.72 2.3
## W09 0.07 0.05 0.08 0.71 -0.07 0.52 0.48 1.1
## W10 0.45 0.03 0.32 0.30 0.16 0.42 0.58 3.0
## W11 0.44 0.18 -0.01 0.23 0.13 0.29 0.71 2.1
## W12 0.58 0.16 0.17 0.21 -0.03 0.44 0.56 1.6
## W13 0.56 0.38 -0.02 0.12 0.16 0.49 0.51 2.1
## W14 0.45 0.21 0.11 0.03 0.07 0.26 0.74 1.6
## W15 0.66 -0.02 0.14 0.07 0.32 0.56 0.44 1.6
## W16 0.02 0.07 0.64 0.22 0.30 0.56 0.44 1.7
## W17 0.50 0.09 0.50 0.06 0.28 0.60 0.40 2.7
## W18 0.44 0.30 0.48 0.13 0.31 0.62 0.38 3.6
## W19 0.40 0.28 0.48 0.15 0.11 0.51 0.49 3.0
## W20 0.30 0.68 0.14 0.01 0.05 0.57 0.43 1.5
## W21 0.29 0.37 0.42 0.02 -0.07 0.40 0.60 2.8
## W22 0.27 0.56 0.14 0.00 0.03 0.40 0.60 1.6
## W23 0.11 0.44 0.25 0.57 0.06 0.60 0.40 2.4
## W24 -0.05 0.62 0.05 0.18 0.19 0.46 0.54 1.4
## W25 0.08 0.50 0.03 0.21 0.23 0.35 0.65 1.9
## W26 0.22 0.12 0.01 0.37 0.18 0.24 0.76 2.4
## W27 0.32 0.43 0.17 0.19 -0.05 0.35 0.65 2.7
## W28 0.18 0.23 0.19 0.29 0.24 0.27 0.73 4.4
##
## MR1 MR2 MR5 MR3 MR4
## SS loadings 3.48 2.59 1.88 1.80 1.18
## Proportion Var 0.13 0.10 0.07 0.07 0.05
## Cumulative Var 0.13 0.23 0.31 0.37 0.42
## Proportion Explained 0.32 0.24 0.17 0.17 0.11
## Cumulative Proportion 0.32 0.56 0.73 0.89 1.00
##
## Mean item complexity = 2.3
## Test of the hypothesis that 5 factors are sufficient.
##
## The degrees of freedom for the null model are 325 and the objective function was 9.59 with Chi Square of 2200.14
## The degrees of freedom for the model are 205 and the objective function was 1.56
##
## The root mean square of the residuals (RMSR) is 0.04
## The df corrected root mean square of the residuals is 0.05
##
## The harmonic number of observations is 240 with the empirical chi square 253.42 with prob < 0.012
## The total number of observations was 240 with Likelihood Chi Square = 352.31 with prob < 7e-10
##
## Tucker Lewis Index of factoring reliability = 0.873
## RMSEA index = 0.055 and the 90 % confidence intervals are 0.045 0.064
## BIC = -771.22
## Fit based upon off diagonal values = 0.98
## Measures of factor score adequacy
## MR1 MR2 MR5 MR3 MR4
## Correlation of (regression) scores with factors 0.87 0.87 0.81 0.83 0.77
## Multiple R square of scores with factors 0.76 0.75 0.66 0.69 0.59
## Minimum correlation of possible factor scores 0.53 0.50 0.31 0.39 0.18summary(dta_7)##
## Factor analysis with Call: fa(r = dta[, 29:54], nfactors = 5, rotate = "varimax")
##
## Test of the hypothesis that 5 factors are sufficient.
## The degrees of freedom for the model is 205 and the objective function was 1.56
## The number of observations was 240 with Chi Square = 352.31 with prob < 7e-10
##
## The root mean square of the residuals (RMSA) is 0.04
## The df corrected root mean square of the residuals is 0.05
##
## Tucker Lewis Index of factoring reliability = 0.873
## RMSEA index = 0.055 and the 10 % confidence intervals are 0.045 0.064
## BIC = -771.22#畫圖，dta_4為斜交轉軸結果，因素間有相關係數
fa.diagram(dta_6)
#畫圖，dta_5為正交轉軸結果，因素為獨立
fa.diagram(dta_7)
與原來問卷的domain分題，差異很大
7.CLDQ平行分析
#資料選第62~90 column
dta_5<-fa.parallel(dta[,62:90])
## Parallel analysis suggests that the number of factors = 6 and the number of components = 3Parallel analysis結論
PCA:the number of components = 3 (x的線) FA:number of factors = 6 (△的線)
#rotate="oblimin"斜交轉軸
dta_6<-fa(dta[62:90], nfactors=6, rotate = "oblimin")
dta_6## Factor Analysis using method = minres
## Call: fa(r = dta[62:90], nfactors = 6, rotate = "oblimin")
## Standardized loadings (pattern matrix) based upon correlation matrix
## MR1 MR2 MR5 MR4 MR3 MR6 h2 u2 com
## C01 0.02 0.03 0.11 0.67 -0.07 -0.10 0.57 0.43 1.1
## C02 0.04 0.11 0.28 0.31 -0.06 -0.45 0.59 0.41 2.7
## C03 0.13 0.17 0.01 0.32 0.26 -0.19 0.45 0.55 3.6
## C04 -0.05 0.03 0.49 0.12 0.16 -0.29 0.49 0.51 2.1
## C05 0.11 -0.04 -0.09 0.77 0.05 -0.07 0.65 0.35 1.1
## C06 0.13 0.13 0.37 0.07 0.09 -0.09 0.38 0.62 1.9
## C07 0.11 -0.05 0.15 0.37 0.04 0.16 0.28 0.72 2.0
## C08 0.00 0.02 0.55 0.11 0.07 -0.03 0.41 0.59 1.1
## C09 0.10 -0.02 0.35 0.07 0.16 0.28 0.32 0.68 2.7
## C10 0.69 -0.12 0.17 -0.07 0.08 -0.06 0.55 0.45 1.3
## C11 0.19 0.01 0.71 -0.02 -0.01 0.05 0.66 0.34 1.2
## C12 0.68 0.03 0.11 -0.03 0.03 -0.02 0.58 0.42 1.1
## C13 0.08 0.00 0.52 0.05 0.07 -0.06 0.40 0.60 1.1
## C14 0.03 0.05 0.29 0.29 0.07 0.31 0.37 0.63 3.2
## C15 0.80 0.05 -0.04 0.05 0.05 -0.06 0.73 0.27 1.0
## C16 -0.03 -0.01 0.03 0.02 0.91 -0.03 0.83 0.17 1.0
## C17 0.01 0.03 0.06 0.79 0.01 0.08 0.69 0.31 1.0
## C18 -0.10 0.57 0.10 0.14 0.13 0.16 0.45 0.55 1.6
## C19 0.73 0.08 -0.05 0.22 -0.06 0.12 0.74 0.26 1.3
## C20 0.06 0.03 -0.04 -0.05 0.86 0.05 0.76 0.24 1.0
## C21 0.24 0.03 0.29 -0.08 0.11 0.07 0.25 0.75 2.6
## C22 0.01 0.68 -0.07 0.11 0.10 0.06 0.55 0.45 1.1
## C23 0.24 -0.05 0.25 0.13 -0.03 0.03 0.23 0.77 2.7
## C24 0.73 0.13 0.03 -0.01 0.03 0.03 0.68 0.32 1.1
## C25 0.03 0.97 -0.02 -0.04 -0.01 -0.02 0.94 0.06 1.0
## C26 0.03 0.25 0.52 0.08 -0.05 -0.05 0.49 0.51 1.5
## C27 0.06 0.05 0.34 -0.06 0.07 0.17 0.17 0.83 1.8
## C28 0.11 0.73 0.09 -0.06 -0.03 -0.07 0.65 0.35 1.1
## C29 0.01 0.27 0.12 0.01 -0.09 0.34 0.21 0.79 2.3
##
## MR1 MR2 MR5 MR4 MR3 MR6
## SS loadings 3.57 2.85 3.11 2.75 2.01 0.79
## Proportion Var 0.12 0.10 0.11 0.09 0.07 0.03
## Cumulative Var 0.12 0.22 0.33 0.42 0.49 0.52
## Proportion Explained 0.24 0.19 0.21 0.18 0.13 0.05
## Cumulative Proportion 0.24 0.43 0.63 0.81 0.95 1.00
##
## With factor correlations of
## MR1 MR2 MR5 MR4 MR3 MR6
## MR1 1.00 0.53 0.54 0.50 0.39 0.01
## MR2 0.53 1.00 0.34 0.32 0.27 -0.01
## MR5 0.54 0.34 1.00 0.43 0.30 -0.13
## MR4 0.50 0.32 0.43 1.00 0.23 -0.12
## MR3 0.39 0.27 0.30 0.23 1.00 0.02
## MR6 0.01 -0.01 -0.13 -0.12 0.02 1.00
##
## Mean item complexity = 1.7
## Test of the hypothesis that 6 factors are sufficient.
##
## The degrees of freedom for the null model are 406 and the objective function was 15.47 with Chi Square of 3534.83
## The degrees of freedom for the model are 247 and the objective function was 2.03
##
## The root mean square of the residuals (RMSR) is 0.04
## The df corrected root mean square of the residuals is 0.05
##
## The harmonic number of observations is 240 with the empirical chi square 247.4 with prob < 0.48
## The total number of observations was 240 with Likelihood Chi Square = 455.23 with prob < 1.6e-14
##
## Tucker Lewis Index of factoring reliability = 0.888
## RMSEA index = 0.059 and the 90 % confidence intervals are 0.051 0.068
## BIC = -898.48
## Fit based upon off diagonal values = 0.99
## Measures of factor score adequacy
## MR1 MR2 MR5 MR4 MR3 MR6
## Correlation of (regression) scores with factors 0.95 0.98 0.92 0.93 0.94 0.78
## Multiple R square of scores with factors 0.91 0.96 0.84 0.86 0.89 0.61
## Minimum correlation of possible factor scores 0.81 0.92 0.69 0.73 0.79 0.21summary(dta_6)##
## Factor analysis with Call: fa(r = dta[62:90], nfactors = 6, rotate = "oblimin")
##
## Test of the hypothesis that 6 factors are sufficient.
## The degrees of freedom for the model is 247 and the objective function was 2.03
## The number of observations was 240 with Chi Square = 455.23 with prob < 1.6e-14
##
## The root mean square of the residuals (RMSA) is 0.04
## The df corrected root mean square of the residuals is 0.05
##
## Tucker Lewis Index of factoring reliability = 0.888
## RMSEA index = 0.059 and the 10 % confidence intervals are 0.051 0.068
## BIC = -898.48
## With factor correlations of
## MR1 MR2 MR5 MR4 MR3 MR6
## MR1 1.00 0.53 0.54 0.50 0.39 0.01
## MR2 0.53 1.00 0.34 0.32 0.27 -0.01
## MR5 0.54 0.34 1.00 0.43 0.30 -0.13
## MR4 0.50 0.32 0.43 1.00 0.23 -0.12
## MR3 0.39 0.27 0.30 0.23 1.00 0.02
## MR6 0.01 -0.01 -0.13 -0.12 0.02 1.00#以正交轉軸再做一次
dta_7<-fa(dta[,62:90], nfactors=6, rotate = "varimax")
dta_7## Factor Analysis using method = minres
## Call: fa(r = dta[, 62:90], nfactors = 6, rotate = "varimax")
## Standardized loadings (pattern matrix) based upon correlation matrix
## MR5 MR1 MR2 MR4 MR3 MR6 h2 u2 com
## C01 0.30 0.14 0.12 0.66 -0.02 0.04 0.57 0.43 1.6
## C02 0.56 0.15 0.17 0.40 -0.02 -0.24 0.59 0.41 2.6
## C03 0.28 0.24 0.27 0.40 0.29 -0.05 0.45 0.55 4.3
## C04 0.62 0.11 0.10 0.23 0.17 -0.04 0.49 0.51 1.6
## C05 0.16 0.20 0.09 0.75 0.09 0.02 0.65 0.35 1.3
## C06 0.46 0.24 0.20 0.19 0.13 0.12 0.38 0.62 2.8
## C07 0.17 0.18 0.05 0.38 0.08 0.25 0.28 0.72 2.9
## C08 0.54 0.14 0.08 0.20 0.10 0.20 0.41 0.59 1.9
## C09 0.23 0.19 0.06 0.13 0.19 0.42 0.32 0.68 2.8
## C10 0.34 0.61 0.08 0.14 0.16 0.13 0.55 0.45 2.0
## C11 0.64 0.30 0.11 0.13 0.06 0.35 0.66 0.34 2.2
## C12 0.29 0.62 0.22 0.17 0.13 0.15 0.58 0.42 2.1
## C13 0.54 0.20 0.08 0.16 0.11 0.17 0.40 0.60 1.9
## C14 0.19 0.15 0.13 0.30 0.11 0.43 0.37 0.63 3.0
## C15 0.22 0.71 0.26 0.27 0.15 0.10 0.73 0.27 2.0
## C16 0.19 0.13 0.10 0.10 0.86 0.08 0.83 0.17 1.2
## C17 0.20 0.15 0.14 0.75 0.05 0.19 0.69 0.31 1.5
## C18 0.14 0.09 0.55 0.18 0.17 0.25 0.45 0.55 2.1
## C19 0.14 0.66 0.28 0.37 0.06 0.25 0.74 0.26 2.5
## C20 0.10 0.19 0.14 0.04 0.82 0.13 0.76 0.24 1.3
## C21 0.29 0.28 0.11 0.04 0.15 0.22 0.25 0.75 3.8
## C22 0.08 0.17 0.67 0.18 0.15 0.12 0.55 0.45 1.5
## C23 0.28 0.26 0.05 0.21 0.02 0.17 0.23 0.77 3.7
## C24 0.22 0.66 0.32 0.19 0.14 0.18 0.68 0.32 2.2
## C25 0.17 0.21 0.92 0.07 0.05 0.08 0.94 0.06 1.2
## C26 0.55 0.18 0.29 0.19 0.01 0.19 0.49 0.51 2.4
## C27 0.23 0.13 0.09 0.00 0.10 0.29 0.17 0.83 2.8
## C28 0.26 0.24 0.72 0.07 0.04 0.07 0.65 0.35 1.6
## C29 -0.02 0.08 0.26 0.01 -0.05 0.36 0.21 0.79 2.0
##
## MR5 MR1 MR2 MR4 MR3 MR6
## SS loadings 3.27 3.02 2.86 2.79 1.82 1.31
## Proportion Var 0.11 0.10 0.10 0.10 0.06 0.05
## Cumulative Var 0.11 0.22 0.32 0.41 0.47 0.52
## Proportion Explained 0.22 0.20 0.19 0.18 0.12 0.09
## Cumulative Proportion 0.22 0.42 0.61 0.79 0.91 1.00
##
## Mean item complexity = 2.2
## Test of the hypothesis that 6 factors are sufficient.
##
## The degrees of freedom for the null model are 406 and the objective function was 15.47 with Chi Square of 3534.83
## The degrees of freedom for the model are 247 and the objective function was 2.03
##
## The root mean square of the residuals (RMSR) is 0.04
## The df corrected root mean square of the residuals is 0.05
##
## The harmonic number of observations is 240 with the empirical chi square 247.4 with prob < 0.48
## The total number of observations was 240 with Likelihood Chi Square = 455.23 with prob < 1.6e-14
##
## Tucker Lewis Index of factoring reliability = 0.888
## RMSEA index = 0.059 and the 90 % confidence intervals are 0.051 0.068
## BIC = -898.48
## Fit based upon off diagonal values = 0.99
## Measures of factor score adequacy
## MR5 MR1 MR2 MR4 MR3 MR6
## Correlation of (regression) scores with factors 0.88 0.88 0.97 0.90 0.93 0.77
## Multiple R square of scores with factors 0.77 0.78 0.94 0.80 0.87 0.60
## Minimum correlation of possible factor scores 0.54 0.57 0.87 0.61 0.73 0.19summary(dta_7)##
## Factor analysis with Call: fa(r = dta[, 62:90], nfactors = 6, rotate = "varimax")
##
## Test of the hypothesis that 6 factors are sufficient.
## The degrees of freedom for the model is 247 and the objective function was 2.03
## The number of observations was 240 with Chi Square = 455.23 with prob < 1.6e-14
##
## The root mean square of the residuals (RMSA) is 0.04
## The df corrected root mean square of the residuals is 0.05
##
## Tucker Lewis Index of factoring reliability = 0.888
## RMSEA index = 0.059 and the 10 % confidence intervals are 0.051 0.068
## BIC = -898.48#畫圖，dta_4為斜交轉軸結果，因素間有相關係數
fa.diagram(dta_6)
#畫圖，dta_5為正交轉軸結果，因素為獨立
fa.diagram(dta_7)
與原來問卷的factor分題，差異很大
8.CFA依題目
CLDQ CFA(依原著)
指定6個domain，依照原問卷指定題目到各個domain
#default是用ML法估算
library(lavaan)## This is lavaan 0.6-9
## lavaan is FREE software! Please report any bugs.##
## 載入套件：'lavaan'## 下列物件被遮斷自 'package:psych':
##
## cor2cov#CLDQ跑CFA
M<-
'
AS=~C01+C05+C17
FA=~C02+C04+C08+C11+C13
SS=~C03+C06+C21+C23+C27
AC=~C07+C09+C14
EF=~C10+C12+C15+C16+C19+C20+C24+C26
WO=~C18+C22+C25+C28+C29
'
#fit.measures=T，常見的適配度資料
#standardized=T，係數標準化
#經標準化後，factor loading:0-1，兩個變項的相關性是標準化係數
fit1<-cfa(M, data=dta,estimator="ML")
#CFI,TLI都要>0.9
#RMSEA,SRMR都要<0.08
#以上都滿足才是好模型
summary(fit1, fit.measures=T,standardized=T)## lavaan 0.6-9 ended normally after 50 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 73
##
## Number of observations 240
##
## Model Test User Model:
##
## Test statistic 979.649
## Degrees of freedom 362
## P-value (Chi-square) 0.000
##
## Model Test Baseline Model:
##
## Test statistic 3712.727
## Degrees of freedom 406
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 0.813
## Tucker-Lewis Index (TLI) 0.791
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -11101.666
## Loglikelihood unrestricted model (H1) -10611.841
##
## Akaike (AIC) 22349.331
## Bayesian (BIC) 22603.418
## Sample-size adjusted Bayesian (BIC) 22372.026
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.084
## 90 Percent confidence interval - lower 0.078
## 90 Percent confidence interval - upper 0.091
## P-value RMSEA <= 0.05 0.000
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.070
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## AS =~
## C01 1.000 0.990 0.731
## C05 0.868 0.075 11.606 0.000 0.860 0.803
## C17 1.085 0.089 12.160 0.000 1.074 0.872
## FA =~
## C02 1.000 0.973 0.605
## C04 0.998 0.124 8.068 0.000 0.971 0.661
## C08 1.050 0.130 8.110 0.000 1.022 0.666
## C11 1.140 0.128 8.903 0.000 1.109 0.767
## C13 0.853 0.110 7.745 0.000 0.830 0.625
## SS =~
## C03 1.000 0.949 0.596
## C06 0.861 0.110 7.796 0.000 0.817 0.599
## C21 0.811 0.129 6.285 0.000 0.769 0.459
## C23 0.833 0.133 6.256 0.000 0.790 0.457
## C27 0.613 0.133 4.604 0.000 0.582 0.323
## AC =~
## C07 1.000 0.791 0.590
## C09 1.015 0.176 5.755 0.000 0.802 0.489
## C14 1.088 0.158 6.867 0.000 0.861 0.637
## EF =~
## C10 1.000 1.013 0.709
## C12 1.012 0.091 11.128 0.000 1.025 0.754
## C15 0.979 0.080 12.295 0.000 0.992 0.836
## C16 0.798 0.124 6.458 0.000 0.809 0.435
## C19 0.963 0.080 11.985 0.000 0.976 0.814
## C20 0.770 0.119 6.494 0.000 0.780 0.438
## C24 1.027 0.085 12.091 0.000 1.040 0.822
## C26 0.726 0.092 7.925 0.000 0.736 0.535
## WO =~
## C18 1.000 0.970 0.621
## C22 1.072 0.114 9.369 0.000 1.040 0.718
## C25 1.436 0.130 11.076 0.000 1.392 0.953
## C28 1.129 0.109 10.357 0.000 1.095 0.824
## C29 0.502 0.118 4.254 0.000 0.487 0.291
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## AS ~~
## FA 0.582 0.104 5.590 0.000 0.604 0.604
## SS 0.639 0.111 5.764 0.000 0.680 0.680
## AC 0.506 0.094 5.364 0.000 0.646 0.646
## EF 0.594 0.098 6.049 0.000 0.592 0.592
## WO 0.338 0.081 4.189 0.000 0.352 0.352
## FA ~~
## SS 0.835 0.138 6.045 0.000 0.904 0.904
## AC 0.528 0.102 5.167 0.000 0.686 0.686
## EF 0.711 0.116 6.105 0.000 0.721 0.721
## WO 0.422 0.091 4.637 0.000 0.447 0.447
## SS ~~
## AC 0.641 0.115 5.564 0.000 0.853 0.853
## EF 0.853 0.130 6.575 0.000 0.887 0.887
## WO 0.573 0.107 5.343 0.000 0.623 0.623
## AC ~~
## EF 0.570 0.100 5.688 0.000 0.711 0.711
## WO 0.300 0.078 3.854 0.000 0.390 0.390
## EF ~~
## WO 0.605 0.102 5.936 0.000 0.616 0.616
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .C01 0.855 0.095 8.986 0.000 0.855 0.466
## .C05 0.406 0.053 7.657 0.000 0.406 0.355
## .C17 0.365 0.066 5.530 0.000 0.365 0.240
## .C02 1.643 0.166 9.866 0.000 1.643 0.634
## .C04 1.215 0.128 9.480 0.000 1.215 0.563
## .C08 1.310 0.139 9.440 0.000 1.310 0.556
## .C11 0.860 0.105 8.205 0.000 0.860 0.412
## .C13 1.074 0.110 9.741 0.000 1.074 0.609
## .C03 1.637 0.164 9.966 0.000 1.637 0.645
## .C06 1.191 0.120 9.940 0.000 1.191 0.641
## .C21 2.216 0.209 10.588 0.000 2.216 0.789
## .C23 2.370 0.224 10.595 0.000 2.370 0.791
## .C27 2.901 0.268 10.822 0.000 2.901 0.896
## .C07 1.170 0.132 8.863 0.000 1.170 0.652
## .C09 2.050 0.210 9.783 0.000 2.050 0.761
## .C14 1.087 0.133 8.191 0.000 1.087 0.595
## .C10 1.019 0.102 9.992 0.000 1.019 0.498
## .C12 0.797 0.082 9.692 0.000 0.797 0.431
## .C15 0.424 0.049 8.718 0.000 0.424 0.301
## .C16 2.794 0.260 10.733 0.000 2.794 0.810
## .C19 0.485 0.054 9.065 0.000 0.485 0.337
## .C20 2.565 0.239 10.730 0.000 2.565 0.808
## .C24 0.521 0.058 8.956 0.000 0.521 0.325
## .C26 1.351 0.128 10.574 0.000 1.351 0.714
## .C18 1.501 0.144 10.417 0.000 1.501 0.615
## .C22 1.017 0.102 9.967 0.000 1.017 0.485
## .C25 0.195 0.064 3.047 0.002 0.195 0.091
## .C28 0.566 0.066 8.613 0.000 0.566 0.321
## .C29 2.557 0.235 10.883 0.000 2.557 0.915
## AS 0.981 0.158 6.209 0.000 1.000 1.000
## FA 0.947 0.197 4.817 0.000 1.000 1.000
## SS 0.901 0.190 4.748 0.000 1.000 1.000
## AC 0.626 0.147 4.268 0.000 1.000 1.000
## EF 1.027 0.167 6.140 0.000 1.000 1.000
## WO 0.940 0.181 5.186 0.000 1.000 1.000結果模型不好(CFI:0.813，之後都不用看了)
CLDQ CFA(設相關)
設相關，但題目與原問卷歸因一致，此部分結果未在PPT呈現
#題目與原問卷歸因一致
MM2<-
'
AS=~C01+C05+C17
FA=~C02+C04+C08+C11+C13
SS=~C03+C06+C21+C23+C27
AC=~C07+C09+C14
EF=~C10+C12+C15+C16+C19+C20+C24+C26
WO=~C18+C22+C25+C28+C29
#指定相關
C16~~C20
C08~~C11
C11~~C09
C19~~C26
C01~~C02
C13~~C27
'
fit2a<-cfa(MM2, data=dta,estimator="ML")
summary(fit2a, fit.measures=T,standardized=T)## lavaan 0.6-9 ended normally after 55 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 79
##
## Number of observations 240
##
## Model Test User Model:
##
## Test statistic 664.600
## Degrees of freedom 356
## P-value (Chi-square) 0.000
##
## Model Test Baseline Model:
##
## Test statistic 3712.727
## Degrees of freedom 406
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 0.907
## Tucker-Lewis Index (TLI) 0.894
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -10944.141
## Loglikelihood unrestricted model (H1) -10611.841
##
## Akaike (AIC) 22046.282
## Bayesian (BIC) 22321.253
## Sample-size adjusted Bayesian (BIC) 22070.842
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.060
## 90 Percent confidence interval - lower 0.053
## 90 Percent confidence interval - upper 0.067
## P-value RMSEA <= 0.05 0.010
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.061
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## AS =~
## C01 1.000 0.961 0.719
## C05 0.893 0.078 11.485 0.000 0.859 0.802
## C17 1.113 0.093 12.010 0.000 1.070 0.868
## FA =~
## C02 1.000 1.000 0.627
## C04 1.025 0.119 8.579 0.000 1.025 0.698
## C08 0.893 0.121 7.380 0.000 0.893 0.582
## C11 1.001 0.116 8.594 0.000 1.001 0.698
## C13 0.868 0.106 8.173 0.000 0.868 0.651
## SS =~
## C03 1.000 0.966 0.606
## C06 0.840 0.108 7.810 0.000 0.811 0.595
## C21 0.794 0.126 6.285 0.000 0.767 0.458
## C23 0.816 0.130 6.256 0.000 0.788 0.455
## C27 0.565 0.130 4.338 0.000 0.546 0.303
## AC =~
## C07 1.000 0.817 0.610
## C09 0.933 0.165 5.644 0.000 0.762 0.466
## C14 1.071 0.153 7.022 0.000 0.876 0.648
## EF =~
## C10 1.000 1.000 0.699
## C12 1.015 0.093 10.935 0.000 1.016 0.747
## C15 0.982 0.081 12.049 0.000 0.982 0.828
## C16 0.727 0.125 5.812 0.000 0.727 0.392
## C19 1.002 0.083 12.092 0.000 1.002 0.835
## C20 0.703 0.120 5.858 0.000 0.703 0.395
## C24 1.038 0.087 11.947 0.000 1.039 0.820
## C26 0.792 0.094 8.394 0.000 0.792 0.576
## WO =~
## C18 1.000 0.970 0.621
## C22 1.072 0.114 9.371 0.000 1.040 0.718
## C25 1.434 0.129 11.083 0.000 1.391 0.952
## C28 1.129 0.109 10.364 0.000 1.096 0.825
## C29 0.504 0.118 4.268 0.000 0.489 0.292
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .C16 ~~
## .C20 2.121 0.230 9.212 0.000 2.121 0.758
## .C08 ~~
## .C11 0.488 0.105 4.630 0.000 0.488 0.381
## .C11 ~~
## .C09 0.473 0.102 4.643 0.000 0.473 0.318
## .C19 ~~
## .C26 -0.276 0.057 -4.863 0.000 -0.276 -0.372
## .C01 ~~
## .C02 0.385 0.089 4.324 0.000 0.385 0.333
## .C13 ~~
## .C27 0.495 0.126 3.944 0.000 0.495 0.286
## AS ~~
## FA 0.598 0.112 5.349 0.000 0.623 0.623
## SS 0.646 0.110 5.849 0.000 0.695 0.695
## AC 0.513 0.094 5.463 0.000 0.652 0.652
## EF 0.594 0.096 6.158 0.000 0.618 0.618
## WO 0.329 0.079 4.182 0.000 0.352 0.352
## FA ~~
## SS 0.862 0.140 6.159 0.000 0.892 0.892
## AC 0.513 0.102 5.043 0.000 0.627 0.627
## EF 0.728 0.117 6.213 0.000 0.728 0.728
## WO 0.432 0.093 4.635 0.000 0.445 0.445
## SS ~~
## AC 0.663 0.117 5.645 0.000 0.840 0.840
## EF 0.855 0.129 6.599 0.000 0.884 0.884
## WO 0.588 0.109 5.393 0.000 0.627 0.627
## AC ~~
## EF 0.565 0.099 5.693 0.000 0.691 0.691
## WO 0.299 0.079 3.803 0.000 0.377 0.377
## EF ~~
## WO 0.607 0.102 5.968 0.000 0.626 0.626
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .C01 0.864 0.095 9.111 0.000 0.864 0.483
## .C05 0.408 0.053 7.693 0.000 0.408 0.356
## .C17 0.375 0.066 5.683 0.000 0.375 0.247
## .C02 1.546 0.162 9.541 0.000 1.546 0.607
## .C04 1.108 0.125 8.861 0.000 1.108 0.513
## .C08 1.556 0.161 9.674 0.000 1.556 0.661
## .C11 1.053 0.118 8.922 0.000 1.053 0.513
## .C13 1.022 0.109 9.339 0.000 1.022 0.576
## .C03 1.604 0.163 9.834 0.000 1.604 0.632
## .C06 1.200 0.121 9.922 0.000 1.200 0.646
## .C21 2.219 0.210 10.564 0.000 2.219 0.790
## .C23 2.374 0.225 10.570 0.000 2.374 0.793
## .C27 2.942 0.272 10.825 0.000 2.942 0.908
## .C07 1.127 0.131 8.603 0.000 1.127 0.628
## .C09 2.094 0.211 9.910 0.000 2.094 0.783
## .C14 1.060 0.132 8.014 0.000 1.060 0.580
## .C10 1.045 0.103 10.134 0.000 1.045 0.511
## .C12 0.817 0.083 9.867 0.000 0.817 0.442
## .C15 0.444 0.049 9.061 0.000 0.444 0.315
## .C16 2.920 0.270 10.800 0.000 2.920 0.847
## .C19 0.435 0.050 8.617 0.000 0.435 0.302
## .C20 2.679 0.248 10.798 0.000 2.679 0.844
## .C24 0.525 0.057 9.168 0.000 0.525 0.327
## .C26 1.266 0.122 10.363 0.000 1.266 0.669
## .C18 1.500 0.144 10.414 0.000 1.500 0.614
## .C22 1.017 0.102 9.965 0.000 1.017 0.484
## .C25 0.198 0.063 3.127 0.002 0.198 0.093
## .C28 0.564 0.066 8.610 0.000 0.564 0.320
## .C29 2.555 0.235 10.881 0.000 2.555 0.915
## AS 0.924 0.150 6.153 0.000 1.000 1.000
## FA 1.000 0.198 5.056 0.000 1.000 1.000
## SS 0.933 0.193 4.827 0.000 1.000 1.000
## AC 0.668 0.151 4.420 0.000 1.000 1.000
## EF 1.001 0.165 6.055 0.000 1.000 1.000
## WO 0.941 0.181 5.189 0.000 1.000 1.000TLI:0.894，未>0.9，模型不成立
CLDQ CFA(設相關調整構面)
設定相關，並將C26自EF domain，改為FA domain
MM<-
'
AS=~C01+C05+C17
FA=~C02+C04+C08+C11+C13+C26
#C26提改成FA這個domain
SS=~C03+C06+C21+C23+C27
AC=~C07+C09+C14
EF=~C10+C12+C15+C16+C19+C20+C24
#EF domain刪除C26
WO=~C18+C22+C25+C28+C29
#指定相關
C16~~C20
C08~~C11
C11~~C09
C19~~C26
C01~~C02
C13~~C27
'
fit2<-cfa(MM, data=dta,estimator="ML")
summary(fit2, fit.measures=T,standardized=T)## lavaan 0.6-9 ended normally after 60 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 79
##
## Number of observations 240
##
## Model Test User Model:
##
## Test statistic 635.989
## Degrees of freedom 356
## P-value (Chi-square) 0.000
##
## Model Test Baseline Model:
##
## Test statistic 3712.727
## Degrees of freedom 406
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 0.915
## Tucker-Lewis Index (TLI) 0.903
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -10929.835
## Loglikelihood unrestricted model (H1) -10611.841
##
## Akaike (AIC) 22017.671
## Bayesian (BIC) 22292.641
## Sample-size adjusted Bayesian (BIC) 22042.231
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.057
## 90 Percent confidence interval - lower 0.050
## 90 Percent confidence interval - upper 0.064
## P-value RMSEA <= 0.05 0.050
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.057
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## AS =~
## C01 1.000 0.967 0.722
## C05 0.884 0.077 11.500 0.000 0.855 0.799
## C17 1.109 0.092 12.083 0.000 1.073 0.870
## FA =~
## C02 1.000 0.981 0.616
## C04 0.999 0.120 8.345 0.000 0.979 0.667
## C08 0.922 0.123 7.517 0.000 0.904 0.589
## C11 1.050 0.119 8.823 0.000 1.029 0.718
## C13 0.867 0.107 8.097 0.000 0.851 0.639
## C26 0.937 0.112 8.400 0.000 0.919 0.671
## SS =~
## C03 1.000 0.953 0.598
## C06 0.853 0.110 7.733 0.000 0.813 0.596
## C21 0.810 0.129 6.273 0.000 0.772 0.461
## C23 0.832 0.133 6.244 0.000 0.793 0.458
## C27 0.585 0.133 4.409 0.000 0.558 0.310
## AC =~
## C07 1.000 0.812 0.606
## C09 0.962 0.168 5.723 0.000 0.782 0.476
## C14 1.078 0.154 7.005 0.000 0.876 0.648
## EF =~
## C10 1.000 1.005 0.702
## C12 1.017 0.093 10.972 0.000 1.021 0.751
## C15 0.997 0.081 12.252 0.000 1.002 0.844
## C16 0.728 0.125 5.827 0.000 0.732 0.394
## C19 1.008 0.083 12.206 0.000 1.013 0.839
## C20 0.712 0.120 5.938 0.000 0.715 0.402
## C24 1.044 0.087 12.035 0.000 1.049 0.828
## WO =~
## C18 1.000 0.970 0.621
## C22 1.071 0.114 9.367 0.000 1.039 0.717
## C25 1.434 0.129 11.083 0.000 1.392 0.953
## C28 1.129 0.109 10.367 0.000 1.095 0.825
## C29 0.502 0.118 4.258 0.000 0.487 0.292
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .C16 ~~
## .C20 2.108 0.230 9.180 0.000 2.108 0.757
## .C08 ~~
## .C11 0.456 0.099 4.593 0.000 0.456 0.368
## .C11 ~~
## .C09 0.454 0.100 4.560 0.000 0.454 0.315
## .C26 ~~
## .C19 -0.177 0.052 -3.375 0.001 -0.177 -0.265
## .C01 ~~
## .C02 0.360 0.088 4.075 0.000 0.360 0.310
## .C13 ~~
## .C27 0.489 0.125 3.910 0.000 0.489 0.279
## AS ~~
## FA 0.614 0.112 5.496 0.000 0.647 0.647
## SS 0.639 0.110 5.808 0.000 0.692 0.692
## AC 0.514 0.094 5.466 0.000 0.655 0.655
## EF 0.572 0.095 5.999 0.000 0.589 0.589
## WO 0.333 0.079 4.203 0.000 0.355 0.355
## FA ~~
## SS 0.844 0.137 6.140 0.000 0.903 0.903
## AC 0.520 0.101 5.165 0.000 0.652 0.652
## EF 0.699 0.114 6.129 0.000 0.709 0.709
## WO 0.477 0.095 5.004 0.000 0.502 0.502
## SS ~~
## AC 0.652 0.116 5.605 0.000 0.842 0.842
## EF 0.825 0.127 6.477 0.000 0.861 0.861
## WO 0.581 0.108 5.369 0.000 0.628 0.628
## AC ~~
## EF 0.550 0.098 5.599 0.000 0.674 0.674
## WO 0.302 0.078 3.848 0.000 0.383 0.383
## EF ~~
## WO 0.593 0.101 5.887 0.000 0.608 0.608
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .C01 0.859 0.095 9.084 0.000 0.859 0.479
## .C05 0.414 0.053 7.779 0.000 0.414 0.362
## .C17 0.369 0.066 5.611 0.000 0.369 0.243
## .C02 1.573 0.160 9.829 0.000 1.573 0.621
## .C04 1.199 0.127 9.471 0.000 1.199 0.556
## .C08 1.537 0.156 9.837 0.000 1.537 0.653
## .C11 0.997 0.110 9.048 0.000 0.997 0.485
## .C13 1.049 0.108 9.679 0.000 1.049 0.592
## .C26 1.033 0.110 9.410 0.000 1.033 0.550
## .C03 1.629 0.165 9.888 0.000 1.629 0.642
## .C06 1.198 0.121 9.905 0.000 1.198 0.644
## .C21 2.211 0.210 10.550 0.000 2.211 0.788
## .C23 2.366 0.224 10.557 0.000 2.366 0.790
## .C27 2.932 0.271 10.818 0.000 2.932 0.904
## .C07 1.135 0.131 8.664 0.000 1.135 0.632
## .C09 2.085 0.212 9.856 0.000 2.085 0.773
## .C14 1.060 0.132 8.024 0.000 1.060 0.580
## .C10 1.037 0.104 10.017 0.000 1.037 0.507
## .C12 0.805 0.083 9.702 0.000 0.805 0.436
## .C15 0.404 0.047 8.529 0.000 0.404 0.287
## .C16 2.913 0.270 10.779 0.000 2.913 0.845
## .C19 0.430 0.050 8.576 0.000 0.430 0.296
## .C20 2.662 0.247 10.771 0.000 2.662 0.839
## .C24 0.504 0.057 8.826 0.000 0.504 0.314
## .C18 1.500 0.144 10.415 0.000 1.500 0.614
## .C22 1.019 0.102 9.970 0.000 1.019 0.485
## .C25 0.196 0.064 3.079 0.002 0.196 0.092
## .C28 0.565 0.066 8.602 0.000 0.565 0.320
## .C29 2.556 0.235 10.882 0.000 2.556 0.915
## AS 0.936 0.151 6.181 0.000 1.000 1.000
## FA 0.962 0.192 5.006 0.000 1.000 1.000
## SS 0.909 0.191 4.752 0.000 1.000 1.000
## AC 0.660 0.150 4.395 0.000 1.000 1.000
## EF 1.009 0.166 6.066 0.000 1.000 1.000
## WO 0.941 0.181 5.189 0.000 1.000 1.000模型成立
semPlot繪圖
#繪圖
#install.packages("semPlot")
library(semPlot)
#png('cfa_plot.png',width=1920,height=1080)
semPaths(fit2, whatLabels='std', residual=F,
fixedStyle=c('black', lty=1),
freeStyle=c('black', lty=1),
egde.label.position=.4)
#dev.off()但畫出來很醜
WHOQOL-BREF CFA(依原著)
指定4個domain，依照原問卷指定題目到各個domain
M<-
'
Phy=~W03+W04+W10+W15+W16+W17+W18
Psy=~W05+W06+W07+W11+W19+W26
Soc=~W20+W21+W22+W27
Env=~W08+W09+W12+W13+W14+W23+W24+W25+W28
'
fit3<-cfa(M, data=dta)
summary(fit3,fit.measures=T, standardized=T)## lavaan 0.6-9 ended normally after 75 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 58
##
## Number of observations 240
##
## Model Test User Model:
##
## Test statistic 726.979
## Degrees of freedom 293
## P-value (Chi-square) 0.000
##
## Model Test Baseline Model:
##
## Test statistic 2300.796
## Degrees of freedom 325
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 0.780
## Tucker-Lewis Index (TLI) 0.756
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -7211.852
## Loglikelihood unrestricted model (H1) -6848.362
##
## Akaike (AIC) 14539.704
## Bayesian (BIC) 14741.581
## Sample-size adjusted Bayesian (BIC) 14557.735
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.079
## 90 Percent confidence interval - lower 0.071
## 90 Percent confidence interval - upper 0.086
## P-value RMSEA <= 0.05 0.000
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.071
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## Phy =~
## W03 1.000 0.302 0.289
## W04 1.724 0.467 3.690 0.000 0.520 0.433
## W10 1.700 0.419 4.059 0.000 0.513 0.614
## W15 2.033 0.500 4.064 0.000 0.613 0.618
## W16 1.755 0.449 3.905 0.000 0.529 0.521
## W17 1.899 0.450 4.223 0.000 0.573 0.775
## W18 2.016 0.476 4.236 0.000 0.608 0.793
## Psy =~
## W05 1.000 0.558 0.552
## W06 1.091 0.145 7.538 0.000 0.608 0.659
## W07 0.812 0.132 6.167 0.000 0.453 0.492
## W11 0.695 0.113 6.147 0.000 0.387 0.490
## W19 0.974 0.123 7.922 0.000 0.543 0.717
## W26 0.667 0.134 4.965 0.000 0.372 0.375
## Soc =~
## W20 1.000 0.582 0.743
## W21 0.794 0.103 7.737 0.000 0.462 0.561
## W22 0.942 0.108 8.748 0.000 0.549 0.640
## W27 0.742 0.092 8.040 0.000 0.432 0.584
## Env =~
## W08 1.000 0.356 0.431
## W09 0.895 0.210 4.266 0.000 0.319 0.355
## W12 1.643 0.288 5.697 0.000 0.585 0.586
## W13 1.471 0.252 5.832 0.000 0.523 0.618
## W14 1.334 0.268 4.975 0.000 0.475 0.452
## W23 1.323 0.227 5.831 0.000 0.471 0.618
## W24 0.909 0.184 4.936 0.000 0.323 0.445
## W25 1.019 0.201 5.070 0.000 0.363 0.467
## W28 1.062 0.209 5.093 0.000 0.378 0.470
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## Phy ~~
## Psy 0.144 0.039 3.664 0.000 0.853 0.853
## Soc 0.108 0.030 3.620 0.000 0.615 0.615
## Env 0.085 0.025 3.409 0.001 0.795 0.795
## Psy ~~
## Soc 0.259 0.043 5.954 0.000 0.796 0.796
## Env 0.178 0.037 4.846 0.000 0.898 0.898
## Soc ~~
## Env 0.173 0.033 5.176 0.000 0.835 0.835
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .W03 0.996 0.092 10.805 0.000 0.996 0.916
## .W04 1.170 0.111 10.576 0.000 1.170 0.812
## .W10 0.435 0.044 9.956 0.000 0.435 0.623
## .W15 0.610 0.061 9.935 0.000 0.610 0.618
## .W16 0.750 0.073 10.341 0.000 0.750 0.728
## .W17 0.218 0.026 8.431 0.000 0.218 0.400
## .W18 0.218 0.027 8.108 0.000 0.218 0.371
## .W05 0.711 0.070 10.212 0.000 0.711 0.696
## .W06 0.481 0.050 9.595 0.000 0.481 0.565
## .W07 0.641 0.061 10.419 0.000 0.641 0.758
## .W11 0.475 0.046 10.425 0.000 0.475 0.760
## .W19 0.279 0.031 9.012 0.000 0.279 0.486
## .W26 0.845 0.079 10.686 0.000 0.845 0.859
## .W20 0.275 0.036 7.707 0.000 0.275 0.447
## .W21 0.465 0.048 9.791 0.000 0.465 0.685
## .W22 0.435 0.047 9.180 0.000 0.435 0.591
## .W27 0.360 0.037 9.638 0.000 0.360 0.659
## .W08 0.555 0.053 10.556 0.000 0.555 0.814
## .W09 0.703 0.066 10.704 0.000 0.703 0.874
## .W12 0.653 0.065 10.017 0.000 0.653 0.657
## .W13 0.443 0.045 9.836 0.000 0.443 0.618
## .W14 0.880 0.084 10.506 0.000 0.880 0.796
## .W23 0.359 0.036 9.838 0.000 0.359 0.618
## .W24 0.422 0.040 10.521 0.000 0.422 0.802
## .W25 0.472 0.045 10.466 0.000 0.472 0.782
## .W28 0.503 0.048 10.456 0.000 0.503 0.779
## Phy 0.091 0.043 2.140 0.032 1.000 1.000
## Psy 0.311 0.072 4.343 0.000 1.000 1.000
## Soc 0.339 0.056 6.042 0.000 1.000 1.000
## Env 0.127 0.039 3.266 0.001 1.000 1.000結果模型不好(CFI:0.780，之後都不用看了)
WHOQOL-BREF CFA(設相關)
設定相關
MM<-
'
Phy=~W03+W04+W10+W15+W16+W17+W18
Psy=~W05+W06+W07+W11+W19+W26
Soc=~W20+W21+W22+W27
Env=~W08+W09+W12+W13+W14+W23+W24+W25+W28
W09~~W23
W24~~W25
W05~~W12
W20~~W22
W15~~W18
'
fit4<-cfa(MM, data=dta)
summary(fit4,fit.measures=T, standardized=T)## lavaan 0.6-9 ended normally after 81 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 63
##
## Number of observations 240
##
## Model Test User Model:
##
## Test statistic 584.556
## Degrees of freedom 288
## P-value (Chi-square) 0.000
##
## Model Test Baseline Model:
##
## Test statistic 2300.796
## Degrees of freedom 325
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 0.850
## Tucker-Lewis Index (TLI) 0.831
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -7140.640
## Loglikelihood unrestricted model (H1) -6848.362
##
## Akaike (AIC) 14407.280
## Bayesian (BIC) 14626.561
## Sample-size adjusted Bayesian (BIC) 14426.866
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.066
## 90 Percent confidence interval - lower 0.058
## 90 Percent confidence interval - upper 0.073
## P-value RMSEA <= 0.05 0.001
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.064
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## Phy =~
## W03 1.000 0.301 0.289
## W04 1.764 0.467 3.780 0.000 0.531 0.442
## W10 1.645 0.401 4.098 0.000 0.495 0.593
## W15 2.246 0.538 4.178 0.000 0.676 0.681
## W16 1.665 0.426 3.912 0.000 0.501 0.494
## W17 1.883 0.439 4.292 0.000 0.567 0.767
## W18 2.108 0.489 4.315 0.000 0.635 0.828
## Psy =~
## W05 1.000 0.549 0.543
## W06 1.114 0.149 7.452 0.000 0.611 0.662
## W07 0.826 0.135 6.109 0.000 0.453 0.492
## W11 0.710 0.116 6.113 0.000 0.390 0.493
## W19 0.995 0.127 7.821 0.000 0.546 0.720
## W26 0.658 0.137 4.809 0.000 0.361 0.364
## Soc =~
## W20 1.000 0.518 0.662
## W21 0.902 0.123 7.355 0.000 0.468 0.568
## W22 0.909 0.104 8.711 0.000 0.471 0.549
## W27 0.853 0.111 7.680 0.000 0.442 0.598
## Env =~
## W08 1.000 0.345 0.418
## W09 0.733 0.204 3.591 0.000 0.253 0.282
## W12 1.694 0.301 5.624 0.000 0.584 0.585
## W13 1.539 0.266 5.786 0.000 0.531 0.627
## W14 1.413 0.282 5.015 0.000 0.487 0.464
## W23 1.256 0.226 5.551 0.000 0.433 0.568
## W24 0.813 0.181 4.496 0.000 0.280 0.386
## W25 0.960 0.201 4.775 0.000 0.331 0.426
## W28 1.070 0.215 4.987 0.000 0.369 0.459
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .W09 ~~
## .W23 0.226 0.039 5.730 0.000 0.226 0.419
## .W24 ~~
## .W25 0.196 0.034 5.745 0.000 0.196 0.415
## .W05 ~~
## .W12 0.222 0.050 4.450 0.000 0.222 0.324
## .W20 ~~
## .W22 0.137 0.036 3.810 0.000 0.137 0.326
## .W15 ~~
## .W18 -0.127 0.028 -4.543 0.000 -0.127 -0.406
## Phy ~~
## Psy 0.138 0.037 3.684 0.000 0.836 0.836
## Soc 0.104 0.029 3.655 0.000 0.668 0.668
## Env 0.087 0.025 3.440 0.001 0.842 0.842
## Psy ~~
## Soc 0.249 0.043 5.837 0.000 0.877 0.877
## Env 0.174 0.037 4.769 0.000 0.922 0.922
## Soc ~~
## Env 0.167 0.033 5.067 0.000 0.935 0.935
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .W03 0.997 0.092 10.845 0.000 0.997 0.917
## .W04 1.159 0.109 10.659 0.000 1.159 0.804
## .W10 0.453 0.044 10.281 0.000 0.453 0.649
## .W15 0.529 0.059 9.038 0.000 0.529 0.536
## .W16 0.780 0.074 10.561 0.000 0.780 0.756
## .W17 0.225 0.025 9.038 0.000 0.225 0.412
## .W18 0.185 0.026 7.061 0.000 0.185 0.315
## .W05 0.719 0.070 10.239 0.000 0.719 0.705
## .W06 0.478 0.050 9.563 0.000 0.478 0.562
## .W07 0.641 0.062 10.413 0.000 0.641 0.758
## .W11 0.473 0.045 10.411 0.000 0.473 0.757
## .W19 0.276 0.031 8.956 0.000 0.276 0.481
## .W26 0.853 0.080 10.701 0.000 0.853 0.868
## .W20 0.345 0.040 8.599 0.000 0.345 0.562
## .W21 0.460 0.047 9.688 0.000 0.460 0.678
## .W22 0.514 0.053 9.615 0.000 0.514 0.699
## .W27 0.351 0.037 9.445 0.000 0.351 0.643
## .W08 0.563 0.053 10.640 0.000 0.563 0.826
## .W09 0.741 0.068 10.823 0.000 0.741 0.921
## .W12 0.656 0.065 10.126 0.000 0.656 0.658
## .W13 0.435 0.044 9.889 0.000 0.435 0.607
## .W14 0.867 0.082 10.541 0.000 0.867 0.785
## .W23 0.393 0.039 10.199 0.000 0.393 0.677
## .W24 0.448 0.042 10.691 0.000 0.448 0.851
## .W25 0.494 0.047 10.621 0.000 0.494 0.819
## .W28 0.510 0.048 10.552 0.000 0.510 0.789
## Phy 0.091 0.042 2.172 0.030 1.000 1.000
## Psy 0.301 0.070 4.271 0.000 1.000 1.000
## Soc 0.269 0.053 5.109 0.000 1.000 1.000
## Env 0.119 0.037 3.187 0.001 1.000 1.000結果模型不好
WHOQOL-BREF CFA(DWLS)
設定相關，跑DWLS
MMa<-
'
Phy=~W03+W04+W10+W15+W16+W17+W18
Psy=~W05+W06+W07+W11+W19+W26
Soc=~W20+W21+W22+W27
Env=~W08+W09+W12+W13+W14+W23+W24+W25+W28
W09~~W23
W24~~W25
W05~~W12
W20~~W22
W15~~W18
'
fit5<-cfa(MMa, data=dta,estimator="DWLS")## Warning in lav_samplestats_from_data(lavdata = lavdata, lavoptions = lavoptions, : lavaan WARNING: number of observations (240) too small to compute Gammasummary(fit5,fit.measures=T, standardized=T)## lavaan 0.6-9 ended normally after 63 iterations
##
## Estimator DWLS
## Optimization method NLMINB
## Number of model parameters 63
##
## Number of observations 240
##
## Model Test User Model:
##
## Test statistic 264.383
## Degrees of freedom 288
## P-value (Chi-square) 0.838
##
## Model Test Baseline Model:
##
## Test statistic 4657.595
## Degrees of freedom 325
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.006
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.016
## P-value RMSEA <= 0.05 1.000
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.063
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Unstructured
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## Phy =~
## W03 1.000 0.285 0.273
## W04 1.804 0.226 7.967 0.000 0.514 0.428
## W10 1.902 0.225 8.460 0.000 0.542 0.648
## W15 2.244 0.270 8.302 0.000 0.640 0.643
## W16 1.810 0.223 8.123 0.000 0.516 0.507
## W17 1.912 0.223 8.567 0.000 0.545 0.736
## W18 2.304 0.265 8.707 0.000 0.657 0.855
## Psy =~
## W05 1.000 0.533 0.526
## W06 1.141 0.086 13.225 0.000 0.608 0.657
## W07 0.890 0.074 11.978 0.000 0.474 0.514
## W11 0.733 0.061 12.014 0.000 0.390 0.493
## W19 1.000 0.074 13.486 0.000 0.532 0.701
## W26 0.752 0.070 10.800 0.000 0.400 0.403
## Soc =~
## W20 1.000 0.499 0.635
## W21 0.968 0.077 12.626 0.000 0.483 0.585
## W22 0.925 0.073 12.702 0.000 0.461 0.536
## W27 0.904 0.070 12.938 0.000 0.451 0.609
## Env =~
## W08 1.000 0.361 0.437
## W09 0.730 0.084 8.695 0.000 0.264 0.293
## W12 1.593 0.135 11.797 0.000 0.576 0.576
## W13 1.452 0.120 12.075 0.000 0.525 0.618
## W14 1.368 0.123 11.106 0.000 0.494 0.469
## W23 1.229 0.102 12.031 0.000 0.444 0.581
## W24 0.731 0.074 9.851 0.000 0.264 0.363
## W25 0.893 0.085 10.533 0.000 0.323 0.414
## W28 1.071 0.094 11.387 0.000 0.387 0.481
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .W09 ~~
## .W23 0.220 0.066 3.320 0.001 0.220 0.412
## .W24 ~~
## .W25 0.204 0.043 4.767 0.000 0.204 0.425
## .W05 ~~
## .W12 0.234 0.080 2.938 0.003 0.234 0.333
## .W20 ~~
## .W22 0.153 0.064 2.386 0.017 0.153 0.348
## .W15 ~~
## .W18 -0.117 0.069 -1.689 0.091 -0.117 -0.384
## Phy ~~
## Psy 0.124 0.016 8.007 0.000 0.819 0.819
## Soc 0.093 0.012 7.804 0.000 0.657 0.657
## Env 0.084 0.011 7.804 0.000 0.816 0.816
## Psy ~~
## Soc 0.227 0.020 11.317 0.000 0.853 0.853
## Env 0.180 0.017 10.866 0.000 0.933 0.933
## Soc ~~
## Env 0.168 0.015 11.129 0.000 0.934 0.934
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .W03 1.010 0.083 12.183 0.000 1.010 0.926
## .W04 1.182 0.092 12.817 0.000 1.182 0.817
## .W10 0.407 0.068 5.940 0.000 0.407 0.580
## .W15 0.581 0.101 5.745 0.000 0.581 0.587
## .W16 0.769 0.083 9.248 0.000 0.769 0.743
## .W17 0.252 0.065 3.861 0.000 0.252 0.459
## .W18 0.159 0.067 2.393 0.017 0.159 0.270
## .W05 0.743 0.095 7.789 0.000 0.743 0.724
## .W06 0.486 0.094 5.143 0.000 0.486 0.568
## .W07 0.624 0.082 7.649 0.000 0.624 0.735
## .W11 0.475 0.068 7.009 0.000 0.475 0.757
## .W19 0.293 0.066 4.468 0.000 0.293 0.509
## .W26 0.827 0.081 10.224 0.000 0.827 0.838
## .W20 0.368 0.070 5.288 0.000 0.368 0.596
## .W21 0.448 0.085 5.276 0.000 0.448 0.658
## .W22 0.526 0.085 6.194 0.000 0.526 0.712
## .W27 0.346 0.058 6.001 0.000 0.346 0.630
## .W08 0.554 0.081 6.837 0.000 0.554 0.809
## .W09 0.738 0.084 8.776 0.000 0.738 0.914
## .W12 0.668 0.095 7.022 0.000 0.668 0.668
## .W13 0.444 0.074 6.012 0.000 0.444 0.618
## .W14 0.865 0.083 10.418 0.000 0.865 0.780
## .W23 0.386 0.067 5.730 0.000 0.386 0.662
## .W24 0.459 0.049 9.381 0.000 0.459 0.868
## .W25 0.502 0.065 7.785 0.000 0.502 0.828
## .W28 0.499 0.067 7.447 0.000 0.499 0.769
## Phy 0.081 0.017 4.694 0.000 1.000 1.000
## Psy 0.284 0.035 8.142 0.000 1.000 1.000
## Soc 0.249 0.035 7.162 0.000 1.000 1.000
## Env 0.131 0.018 7.352 0.000 1.000 1.000結果跑出warning,警告樣本數不夠，應該不能跑DWLS
處理方法有幾個選擇： (1)放棄，宣布工具不適配 (2)修改工具，修到好為止 (3)增大樣本數，直到至少可以使用DWLS為止 (4)簡化邁進，用domain取代題目
參考老師paper:Su, C. T., Ng, H. S., Yang, A. L., & Lin, C. Y. (2014). Psychometric evaluation of the Short Form 36 Health Survey (SF-36) and the World Health Organization Quality of Life Scale Brief Version (WHOQOL-BREF) for patients with schizophrenia. Psychological Assessment, 26(3), 980.
9.SEM
SemM<-
'
Phy=~W03+W04+W10+W15+W16+W17+W18
Psy=~W05+W06+W07+W11+W19+W26
Soc=~W20+W21+W22+W27
Env=~W08+W09+W12+W13+W14+W23+W24+W25+W28
W09~~W23
W24~~W25
W05~~W12
W20~~W22
W15~~W18
AS=~C01+C05+C17
FA=~C02+C04+C08+C11+C13+C26
SS=~C03+C06+C21+C23+C27
AC=~C07+C09+C14
EF=~C10+C12+C15+C16+C19+C20+C24
WO=~C18+C22+C25+C28+C29
C16~~C20
C08~~C11
C11~~C09
C19~~C26
C01~~C02
C13~~C27
Phy~AS+SS
Psy~EF+FA
Soc~AC
Env~WO
'
fit6<-sem(SemM, data=dta)
summary(fit6,fit.measures=T, standardized=T)## lavaan 0.6-9 ended normally after 118 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 148
##
## Number of observations 240
##
## Model Test User Model:
##
## Test statistic 2628.286
## Degrees of freedom 1392
## P-value (Chi-square) 0.000
##
## Model Test Baseline Model:
##
## Test statistic 7468.942
## Degrees of freedom 1485
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 0.793
## Tucker-Lewis Index (TLI) 0.780
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -18046.637
## Loglikelihood unrestricted model (H1) -16732.494
##
## Akaike (AIC) 36389.273
## Bayesian (BIC) 36904.408
## Sample-size adjusted Bayesian (BIC) 36435.284
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.061
## 90 Percent confidence interval - lower 0.057
## 90 Percent confidence interval - upper 0.064
## P-value RMSEA <= 0.05 0.000
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.093
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## Phy =~
## W03 1.000 0.295 0.284
## W04 1.711 0.469 3.647 0.000 0.505 0.425
## W10 1.642 0.411 3.997 0.000 0.484 0.591
## W15 2.158 0.533 4.050 0.000 0.637 0.657
## W16 1.653 0.434 3.808 0.000 0.488 0.487
## W17 1.822 0.437 4.169 0.000 0.537 0.750
## W18 1.995 0.477 4.183 0.000 0.589 0.794
## Psy =~
## W05 1.000 0.509 0.514
## W06 1.149 0.165 6.959 0.000 0.585 0.649
## W07 0.813 0.147 5.548 0.000 0.414 0.456
## W11 0.724 0.127 5.692 0.000 0.369 0.472
## W19 1.006 0.140 7.208 0.000 0.512 0.694
## W26 0.717 0.151 4.748 0.000 0.365 0.371
## Soc =~
## W20 1.000 0.519 0.666
## W21 0.896 0.122 7.374 0.000 0.465 0.567
## W22 0.917 0.105 8.771 0.000 0.476 0.557
## W27 0.823 0.109 7.521 0.000 0.427 0.580
## Env =~
## W08 1.000 0.347 0.423
## W09 0.736 0.203 3.628 0.000 0.255 0.285
## W12 1.587 0.286 5.549 0.000 0.551 0.559
## W13 1.465 0.255 5.749 0.000 0.508 0.608
## W14 1.356 0.274 4.953 0.000 0.471 0.451
## W23 1.229 0.221 5.569 0.000 0.426 0.565
## W24 0.806 0.179 4.515 0.000 0.280 0.387
## W25 0.940 0.197 4.766 0.000 0.326 0.422
## W28 1.014 0.207 4.891 0.000 0.352 0.441
## AS =~
## C01 1.000 0.967 0.722
## C05 0.882 0.077 11.490 0.000 0.853 0.797
## C17 1.111 0.092 12.118 0.000 1.075 0.872
## FA =~
## C02 1.000 0.977 0.613
## C04 1.009 0.121 8.362 0.000 0.986 0.671
## C08 0.930 0.124 7.526 0.000 0.908 0.592
## C11 1.062 0.120 8.819 0.000 1.038 0.721
## C13 0.867 0.108 8.052 0.000 0.847 0.636
## C26 0.942 0.112 8.373 0.000 0.920 0.671
## SS =~
## C03 1.000 0.981 0.616
## C06 0.825 0.105 7.844 0.000 0.809 0.593
## C21 0.776 0.124 6.264 0.000 0.761 0.454
## C23 0.806 0.128 6.293 0.000 0.790 0.457
## C27 0.566 0.128 4.410 0.000 0.555 0.308
## AC =~
## C07 1.000 0.786 0.587
## C09 1.050 0.177 5.927 0.000 0.825 0.503
## C14 1.093 0.159 6.887 0.000 0.860 0.636
## EF =~
## C10 1.000 1.009 0.705
## C12 1.017 0.092 11.071 0.000 1.026 0.755
## C15 0.995 0.081 12.347 0.000 1.004 0.846
## C16 0.732 0.124 5.891 0.000 0.739 0.398
## C19 0.997 0.082 12.191 0.000 1.005 0.833
## C20 0.711 0.119 5.965 0.000 0.718 0.403
## C24 1.039 0.086 12.094 0.000 1.048 0.828
## WO =~
## C18 1.000 0.975 0.624
## C22 1.074 0.114 9.422 0.000 1.048 0.723
## C25 1.411 0.127 11.098 0.000 1.376 0.942
## C28 1.128 0.108 10.404 0.000 1.100 0.828
## C29 0.507 0.118 4.299 0.000 0.494 0.296
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## Phy ~
## AS 0.059 0.030 1.949 0.051 0.194 0.194
## SS -0.151 0.046 -3.294 0.001 -0.501 -0.501
## Psy ~
## EF -0.146 0.048 -3.045 0.002 -0.289 -0.289
## FA -0.000 0.047 -0.006 0.995 -0.001 -0.001
## Soc ~
## AC -0.054 0.048 -1.126 0.260 -0.081 -0.081
## Env ~
## WO -0.106 0.027 -3.986 0.000 -0.297 -0.297
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .W09 ~~
## .W23 0.220 0.039 5.626 0.000 0.220 0.412
## .W24 ~~
## .W25 0.191 0.034 5.665 0.000 0.191 0.410
## .W05 ~~
## .W12 0.215 0.050 4.299 0.000 0.215 0.310
## .W20 ~~
## .W22 0.129 0.036 3.613 0.000 0.129 0.312
## .W15 ~~
## .W18 -0.115 0.028 -4.074 0.000 -0.115 -0.349
## .C16 ~~
## .C20 2.102 0.229 9.173 0.000 2.102 0.757
## .C08 ~~
## .C11 0.452 0.099 4.564 0.000 0.452 0.367
## .C11 ~~
## .C09 0.438 0.098 4.468 0.000 0.438 0.310
## .C26 ~~
## .C19 -0.175 0.053 -3.310 0.001 -0.175 -0.258
## .C01 ~~
## .C02 0.359 0.088 4.062 0.000 0.359 0.308
## .C13 ~~
## .C27 0.500 0.125 3.987 0.000 0.500 0.284
## AS ~~
## FA 0.612 0.111 5.496 0.000 0.648 0.648
## SS 0.657 0.112 5.884 0.000 0.693 0.693
## AC 0.500 0.092 5.408 0.000 0.657 0.657
## EF 0.570 0.095 5.983 0.000 0.584 0.584
## WO 0.344 0.080 4.286 0.000 0.365 0.365
## FA ~~
## SS 0.848 0.137 6.185 0.000 0.885 0.885
## AC 0.510 0.099 5.142 0.000 0.664 0.664
## EF 0.700 0.114 6.130 0.000 0.710 0.710
## WO 0.488 0.097 5.055 0.000 0.512 0.512
## SS ~~
## AC 0.665 0.117 5.704 0.000 0.863 0.863
## EF 0.829 0.127 6.537 0.000 0.838 0.838
## WO 0.639 0.113 5.654 0.000 0.669 0.669
## AC ~~
## EF 0.541 0.097 5.566 0.000 0.682 0.682
## WO 0.309 0.078 3.948 0.000 0.403 0.403
## EF ~~
## WO 0.613 0.103 5.967 0.000 0.623 0.623
## .Phy ~~
## .Psy 0.109 0.031 3.540 0.000 0.823 0.823
## .Soc 0.092 0.026 3.544 0.000 0.653 0.653
## .Env 0.073 0.022 3.362 0.001 0.814 0.814
## .Psy ~~
## .Soc 0.220 0.039 5.600 0.000 0.871 0.871
## .Env 0.146 0.032 4.627 0.000 0.906 0.906
## .Soc ~~
## .Env 0.165 0.032 5.119 0.000 0.962 0.962
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .W03 0.990 0.091 10.830 0.000 0.990 0.919
## .W04 1.157 0.109 10.639 0.000 1.157 0.820
## .W10 0.437 0.043 10.171 0.000 0.437 0.650
## .W15 0.535 0.058 9.173 0.000 0.535 0.569
## .W16 0.766 0.073 10.508 0.000 0.766 0.763
## .W17 0.225 0.025 8.988 0.000 0.225 0.438
## .W18 0.203 0.027 7.549 0.000 0.203 0.369
## .W05 0.720 0.070 10.268 0.000 0.720 0.736
## .W06 0.470 0.049 9.490 0.000 0.470 0.578
## .W07 0.654 0.063 10.459 0.000 0.654 0.792
## .W11 0.473 0.045 10.410 0.000 0.473 0.777
## .W19 0.282 0.031 9.034 0.000 0.282 0.519
## .W26 0.835 0.078 10.656 0.000 0.835 0.862
## .W20 0.338 0.040 8.505 0.000 0.338 0.557
## .W21 0.457 0.047 9.692 0.000 0.457 0.679
## .W22 0.504 0.053 9.541 0.000 0.504 0.690
## .W27 0.360 0.038 9.590 0.000 0.360 0.663
## .W08 0.554 0.052 10.607 0.000 0.554 0.821
## .W09 0.735 0.068 10.809 0.000 0.735 0.919
## .W12 0.667 0.065 10.187 0.000 0.667 0.687
## .W13 0.441 0.044 9.930 0.000 0.441 0.631
## .W14 0.869 0.082 10.544 0.000 0.869 0.797
## .W23 0.387 0.038 10.156 0.000 0.387 0.680
## .W24 0.444 0.042 10.671 0.000 0.444 0.850
## .W25 0.490 0.046 10.604 0.000 0.490 0.822
## .W28 0.514 0.049 10.567 0.000 0.514 0.806
## .C01 0.857 0.094 9.091 0.000 0.857 0.478
## .C05 0.419 0.053 7.852 0.000 0.419 0.365
## .C17 0.365 0.065 5.577 0.000 0.365 0.240
## .C02 1.584 0.161 9.855 0.000 1.584 0.624
## .C04 1.186 0.126 9.446 0.000 1.186 0.550
## .C08 1.530 0.156 9.829 0.000 1.530 0.650
## .C11 0.992 0.110 9.014 0.000 0.992 0.479
## .C13 1.054 0.109 9.707 0.000 1.054 0.595
## .C26 1.035 0.110 9.424 0.000 1.035 0.550
## .C03 1.576 0.158 9.972 0.000 1.576 0.621
## .C06 1.204 0.119 10.107 0.000 1.204 0.648
## .C21 2.228 0.210 10.603 0.000 2.228 0.794
## .C23 2.370 0.224 10.598 0.000 2.370 0.791
## .C27 2.936 0.271 10.822 0.000 2.936 0.905
## .C07 1.178 0.131 8.972 0.000 1.178 0.656
## .C09 2.015 0.207 9.727 0.000 2.015 0.747
## .C14 1.089 0.131 8.297 0.000 1.089 0.596
## .C10 1.028 0.103 10.002 0.000 1.028 0.503
## .C12 0.796 0.082 9.675 0.000 0.796 0.430
## .C15 0.400 0.047 8.493 0.000 0.400 0.284
## .C16 2.902 0.269 10.774 0.000 2.902 0.842
## .C19 0.445 0.051 8.695 0.000 0.445 0.306
## .C20 2.659 0.247 10.769 0.000 2.659 0.838
## .C24 0.505 0.057 8.835 0.000 0.505 0.315
## .C18 1.491 0.144 10.365 0.000 1.491 0.611
## .C22 1.001 0.101 9.885 0.000 1.001 0.477
## .C25 0.239 0.063 3.811 0.000 0.239 0.112
## .C28 0.554 0.065 8.527 0.000 0.554 0.314
## .C29 2.550 0.235 10.871 0.000 2.550 0.913
## .Phy 0.074 0.035 2.111 0.035 0.846 0.846
## .Psy 0.237 0.060 3.952 0.000 0.916 0.916
## .Soc 0.268 0.052 5.125 0.000 0.993 0.993
## .Env 0.110 0.034 3.198 0.001 0.912 0.912
## AS 0.935 0.151 6.187 0.000 1.000 1.000
## FA 0.954 0.192 4.981 0.000 1.000 1.000
## SS 0.962 0.193 4.983 0.000 1.000 1.000
## AC 0.618 0.145 4.267 0.000 1.000 1.000
## EF 1.017 0.167 6.100 0.000 1.000 1.000
## WO 0.951 0.183 5.209 0.000 1.000 1.000SEM模型不成立
CFI:0.793
10.CFA 依構面
#參考老師paper的作法
knitr::include_graphics("cfamodel1.png")
M1,WHOQOL-BREF CFA(構面)
把所有domain當成一個factor
#domain當成factor
#跑WHOQOL-BREF
M1<-
'
factor1=~W_phy+W_psy+W_soc+W_env
'
fit_M1<-cfa(M1, data=dta)
summary(fit_M1,fit.measures=T, standardized=T)## lavaan 0.6-9 ended normally after 30 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 8
##
## Number of observations 240
##
## Model Test User Model:
##
## Test statistic 2.200
## Degrees of freedom 2
## P-value (Chi-square) 0.333
##
## Model Test Baseline Model:
##
## Test statistic 399.873
## Degrees of freedom 6
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 0.999
## Tucker-Lewis Index (TLI) 0.998
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -2380.414
## Loglikelihood unrestricted model (H1) -2379.314
##
## Akaike (AIC) 4776.828
## Bayesian (BIC) 4804.673
## Sample-size adjusted Bayesian (BIC) 4779.315
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.020
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.131
## P-value RMSEA <= 0.05 0.524
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.014
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## factor1 =~
## W_phy 1.000 2.919 0.681
## W_psy 0.969 0.091 10.696 0.000 2.828 0.813
## W_soc 0.566 0.061 9.269 0.000 1.651 0.681
## W_env 1.299 0.118 10.976 0.000 3.793 0.860
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .W_phy 9.841 1.044 9.429 0.000 9.841 0.536
## .W_psy 4.088 0.565 7.233 0.000 4.088 0.338
## .W_soc 3.151 0.334 9.430 0.000 3.151 0.536
## .W_env 5.080 0.877 5.791 0.000 5.080 0.261
## factor1 8.521 1.512 5.637 0.000 1.000 1.000WHOQOL-BREF CFA(依構面)模型成立
Comparative Fit Index (CFI) 0.999
Tucker-Lewis Index (TLI) 0.998
RMSEA 0.020
SRMR 0.014
M2,CLDQ CFA(構面)
把所有domain當成一個factor
#CLDQ跑CFA
M2<-
'
factor1 =~ C_as+ C_fa+ C_ss+ C_ac+ C_ef+ C_wo
'
fit_M2<-cfa(M2, data=dta)
summary(fit_M2,fit.measures=T, standardized=T)## lavaan 0.6-9 ended normally after 19 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 12
##
## Number of observations 240
##
## Model Test User Model:
##
## Test statistic 14.241
## Degrees of freedom 9
## P-value (Chi-square) 0.114
##
## Model Test Baseline Model:
##
## Test statistic 574.192
## Degrees of freedom 15
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 0.991
## Tucker-Lewis Index (TLI) 0.984
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -1802.412
## Loglikelihood unrestricted model (H1) -1795.292
##
## Akaike (AIC) 3628.825
## Bayesian (BIC) 3670.592
## Sample-size adjusted Bayesian (BIC) 3632.555
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.049
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.095
## P-value RMSEA <= 0.05 0.456
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.027
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## factor1 =~
## C_as 1.000 0.664 0.625
## C_fa 1.248 0.135 9.260 0.000 0.829 0.747
## C_ss 1.225 0.127 9.618 0.000 0.813 0.790
## C_ac 1.040 0.125 8.342 0.000 0.691 0.649
## C_ef 1.278 0.129 9.911 0.000 0.849 0.829
## C_wo 0.779 0.102 7.632 0.000 0.517 0.581
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .C_as 0.687 0.069 9.935 0.000 0.687 0.609
## .C_fa 0.544 0.061 8.918 0.000 0.544 0.442
## .C_ss 0.400 0.048 8.260 0.000 0.400 0.377
## .C_ac 0.654 0.067 9.793 0.000 0.654 0.578
## .C_ef 0.327 0.044 7.380 0.000 0.327 0.312
## .C_wo 0.525 0.052 10.147 0.000 0.525 0.662
## factor1 0.441 0.087 5.086 0.000 1.000 1.000CLDQ CFA(依構面)模型成立
Comparative Fit Index (CFI) 0.991
Tucker-Lewis Index (TLI) 0.984
RMSEA 0.049
SRMR 0.027
11.WHOQOL BREF+CLDQ
#參考老師paper的作法
knitr::include_graphics("model3.png")
M3,兩問卷CFA(ML)
#CLDQ跑CFA
#default是ML
M3<-
'
factor1 =~ W_phy+W_psy+W_soc+W_env
factor2 =~ C_as+ C_fa+ C_ss+ C_ac+ C_ef+ C_wo
factor1~~factor2
#沒做factor1~~factor2也沒關係，系統判定相關
'
fit_M3<-cfa(M3, data=dta)
summary(fit_M3,fit.measures=T, standardized=T)## lavaan 0.6-9 ended normally after 45 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 21
##
## Number of observations 240
##
## Model Test User Model:
##
## Test statistic 90.608
## Degrees of freedom 34
## P-value (Chi-square) 0.000
##
## Model Test Baseline Model:
##
## Test statistic 1103.231
## Degrees of freedom 45
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 0.947
## Tucker-Lewis Index (TLI) 0.929
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -4155.327
## Loglikelihood unrestricted model (H1) -4110.023
##
## Akaike (AIC) 8352.653
## Bayesian (BIC) 8425.747
## Sample-size adjusted Bayesian (BIC) 8359.182
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.083
## 90 Percent confidence interval - lower 0.063
## 90 Percent confidence interval - upper 0.104
## P-value RMSEA <= 0.05 0.005
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.068
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## factor1 =~
## W_phy 1.000 3.035 0.708
## W_psy 0.936 0.083 11.285 0.000 2.839 0.817
## W_soc 0.530 0.056 9.387 0.000 1.609 0.664
## W_env 1.234 0.107 11.559 0.000 3.744 0.849
## factor2 =~
## C_as 1.000 0.649 0.611
## C_fa 1.260 0.140 9.018 0.000 0.818 0.737
## C_ss 1.246 0.132 9.401 0.000 0.808 0.785
## C_ac 1.054 0.129 8.168 0.000 0.684 0.643
## C_ef 1.337 0.136 9.838 0.000 0.868 0.848
## C_wo 0.804 0.106 7.600 0.000 0.522 0.586
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## factor1 ~~
## factor2 -1.037 0.196 -5.286 0.000 -0.526 -0.526
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .W_phy 9.151 0.991 9.239 0.000 9.151 0.498
## .W_psy 4.026 0.545 7.386 0.000 4.026 0.333
## .W_soc 3.288 0.342 9.625 0.000 3.288 0.559
## .W_env 5.442 0.844 6.447 0.000 5.442 0.280
## .C_as 0.707 0.070 10.071 0.000 0.707 0.627
## .C_fa 0.562 0.061 9.161 0.000 0.562 0.457
## .C_ss 0.408 0.048 8.516 0.000 0.408 0.384
## .C_ac 0.663 0.067 9.905 0.000 0.663 0.586
## .C_ef 0.294 0.042 7.088 0.000 0.294 0.281
## .C_wo 0.521 0.051 10.180 0.000 0.521 0.657
## factor1 9.211 1.548 5.952 0.000 1.000 1.000
## factor2 0.421 0.085 4.960 0.000 1.000 1.000WHOQOL-BREF+CLDQ(ML)模型不成立
Comparative Fit Index (CFI) 0.947
Tucker-Lewis Index (TLI) 0.929
RMSEA 0.083(沒有<0.08)
SRMR 0.068
M4,兩問卷CFA(構面新定義)
PysEnv+PsySoc
M4<-
'
f1=~W_phy+C_as+C_ss+C_fa+C_ac+W_env
f2=~W_psy+C_ef+C_wo+W_soc
f1~~f2
'
fit_M4<-cfa(M4, data=dta)
summary(fit_M4,fit.measures=T, standardized=T)## lavaan 0.6-9 ended normally after 59 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 21
##
## Number of observations 240
##
## Model Test User Model:
##
## Test statistic 330.115
## Degrees of freedom 34
## P-value (Chi-square) 0.000
##
## Model Test Baseline Model:
##
## Test statistic 1103.231
## Degrees of freedom 45
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 0.720
## Tucker-Lewis Index (TLI) 0.630
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -4275.080
## Loglikelihood unrestricted model (H1) -4110.023
##
## Akaike (AIC) 8592.161
## Bayesian (BIC) 8665.254
## Sample-size adjusted Bayesian (BIC) 8598.689
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.190
## 90 Percent confidence interval - lower 0.172
## 90 Percent confidence interval - upper 0.209
## P-value RMSEA <= 0.05 0.000
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.126
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## f1 =~
## W_phy 1.000 2.733 0.638
## C_as -0.219 0.029 -7.632 0.000 -0.599 -0.564
## C_ss -0.285 0.029 -9.664 0.000 -0.778 -0.756
## C_fa -0.285 0.031 -9.140 0.000 -0.780 -0.703
## C_ac -0.242 0.029 -8.293 0.000 -0.663 -0.623
## W_env 0.876 0.119 7.376 0.000 2.393 0.542
## f2 =~
## W_psy 1.000 1.900 0.547
## C_ef -0.459 0.053 -8.651 0.000 -0.873 -0.853
## C_wo -0.272 0.039 -6.979 0.000 -0.517 -0.581
## W_soc 0.454 0.095 4.785 0.000 0.863 0.356
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## f1 ~~
## f2 5.155 0.843 6.113 0.000 0.992 0.992
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .W_phy 10.892 1.090 9.989 0.000 10.892 0.593
## .C_as 0.769 0.075 10.303 0.000 0.769 0.682
## .C_ss 0.455 0.050 9.023 0.000 0.455 0.429
## .C_fa 0.623 0.065 9.564 0.000 0.623 0.506
## .C_ac 0.693 0.069 10.064 0.000 0.693 0.612
## .W_env 13.737 1.324 10.374 0.000 13.737 0.706
## .W_psy 8.476 0.819 10.343 0.000 8.476 0.701
## .C_ef 0.285 0.048 5.984 0.000 0.285 0.272
## .C_wo 0.525 0.051 10.218 0.000 0.525 0.662
## .W_soc 5.134 0.478 10.751 0.000 5.134 0.873
## f1 7.470 1.422 5.254 0.000 1.000 1.000
## f2 3.612 0.832 4.342 0.000 1.000 1.000WHOQOL-BREF+CLDQ構面新定義模型不成立
Comparative Fit Index (CFI) 0.72
Tucker-Lewis Index (TLI) 0.63
RMSEA 0.19
SRMR 0.126
#參考老師paper的作法
knitr::include_graphics("cfamodel5.png")
M5,兩問卷CFA(工具+QOL)
M5<-
'
#問卷原定義
WHOQ=~W_phy+W_psy+W_soc+W_env
CLDQ=~C_as+C_ss+C_fa+C_ef+C_ac+C_wo
#依照M4構面新定義為PysEnv+PsySoc
f1=~W_phy+C_as+C_ss+C_fa+C_ac+W_env
f2=~W_psy+C_ef+C_wo+W_soc
WHOQ~~CLDQ
f1~~f2
'
fit_M5<-cfa(M5, data=dta)
summary(fit_M5, fit.measures=T,standardized=T)## lavaan 0.6-9 ended normally after 326 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 36
##
## Number of observations 240
##
## Model Test User Model:
##
## Test statistic 14.293
## Degrees of freedom 19
## P-value (Chi-square) 0.766
##
## Model Test Baseline Model:
##
## Test statistic 1103.231
## Degrees of freedom 45
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.011
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -4117.169
## Loglikelihood unrestricted model (H1) -4110.023
##
## Akaike (AIC) 8306.338
## Bayesian (BIC) 8431.641
## Sample-size adjusted Bayesian (BIC) 8317.530
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.040
## P-value RMSEA <= 0.05 0.982
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.017
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## WHOQ =~
## W_phy 1.000 2.868 0.669
## W_psy 1.254 0.200 6.261 0.000 3.598 1.035
## W_soc 0.855 0.145 5.877 0.000 2.452 1.011
## W_env 2.524 1.025 2.462 0.014 7.238 1.641
## CLDQ =~
## C_as 1.000 1.697 1.598
## C_ss 0.662 0.198 3.338 0.001 1.123 1.090
## C_fa 0.808 0.207 3.904 0.000 1.372 1.236
## C_ef 0.345 0.222 1.551 0.121 0.585 0.572
## C_ac 0.652 0.181 3.593 0.000 1.106 1.040
## C_wo -0.506 1.016 -0.497 0.619 -0.858 -0.963
## f1 =~
## W_phy 1.000 0.353 0.082
## C_as 3.454 8.905 0.388 0.698 1.220 1.149
## C_ss 1.024 2.647 0.387 0.699 0.362 0.351
## C_fa 1.800 4.587 0.392 0.695 0.636 0.573
## C_ac 1.378 3.535 0.390 0.697 0.487 0.458
## W_env -12.097 30.497 -0.397 0.692 -4.275 -0.969
## f2 =~
## W_psy 1.000 1.192 0.343
## C_ef 0.262 0.192 1.367 0.172 0.312 0.305
## C_wo 1.225 1.413 0.867 0.386 1.461 1.640
## W_soc 1.096 0.334 3.279 0.001 1.306 0.539
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## WHOQ ~~
## CLDQ -3.870 2.358 -1.641 0.101 -0.795 -0.795
## f1 ~~
## f2 -0.342 0.609 -0.562 0.574 -0.812 -0.812
## WHOQ ~~
## f1 0.856 1.732 0.494 0.621 0.845 0.845
## f2 -2.569 2.251 -1.141 0.254 -0.751 -0.751
## CLDQ ~~
## f1 -0.545 1.144 -0.476 0.634 -0.909 -0.909
## f2 1.856 1.678 1.106 0.269 0.917 0.917
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .W_phy 8.298 0.955 8.688 0.000 8.298 0.452
## .W_psy 4.167 0.556 7.499 0.000 4.167 0.345
## .W_soc 2.974 0.368 8.092 0.000 2.974 0.506
## .W_env 1.064 4.897 0.217 0.828 1.064 0.055
## .C_as 0.523 0.117 4.477 0.000 0.523 0.463
## .C_ss 0.407 0.047 8.576 0.000 0.407 0.384
## .C_fa 0.531 0.062 8.527 0.000 0.531 0.431
## .C_ef 0.272 0.047 5.789 0.000 0.272 0.260
## .C_ac 0.650 0.067 9.721 0.000 0.650 0.575
## .C_wo 0.223 0.382 0.582 0.560 0.223 0.281
## WHOQ 8.228 3.900 2.110 0.035 1.000 1.000
## CLDQ 2.881 2.332 1.235 0.217 1.000 1.000
## f1 0.125 0.571 0.219 0.827 1.000 1.000
## f2 1.421 1.550 0.917 0.359 1.000 1.000WHOQOL-BREF+CLDQ(工具+QOL)模型成立
Comparative Fit Index (CFI) 1
Tucker-Lewis Index (TLI) 1.011
RMSEA <0.001
SRMR 0.017
M6,兩問卷CFA(工具+QOL2)
M6<-
'
WHOQ=~W_phy+W_psy+W_soc+W_env
CLDQ=~C_as+C_ss+C_fa+C_ef+C_ac+C_wo
f1=~W_phy+C_as+C_ss+C_fa+C_ac+W_env
f2=~W_psy+C_ef+C_wo+W_soc
f1~~f2
#兩個測量工具間未設相關
'
fit_M6<-cfa(M6, data=dta)
summary(fit_M6, fit.measures=T,standardized=T)## lavaan 0.6-9 ended normally after 332 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 36
##
## Number of observations 240
##
## Model Test User Model:
##
## Test statistic 14.293
## Degrees of freedom 19
## P-value (Chi-square) 0.766
##
## Model Test Baseline Model:
##
## Test statistic 1103.231
## Degrees of freedom 45
## P-value 0.000
##
## User Model versus Baseline Model:
##
## Comparative Fit Index (CFI) 1.000
## Tucker-Lewis Index (TLI) 1.011
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -4117.169
## Loglikelihood unrestricted model (H1) -4110.023
##
## Akaike (AIC) 8306.338
## Bayesian (BIC) 8431.641
## Sample-size adjusted Bayesian (BIC) 8317.530
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.000
## 90 Percent confidence interval - lower 0.000
## 90 Percent confidence interval - upper 0.040
## P-value RMSEA <= 0.05 0.982
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.017
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## WHOQ =~
## W_phy 1.000 2.868 0.669
## W_psy 1.254 0.200 6.261 0.000 3.598 1.035
## W_soc 0.855 0.145 5.877 0.000 2.452 1.011
## W_env 2.524 1.025 2.462 0.014 7.238 1.641
## CLDQ =~
## C_as 1.000 1.697 1.598
## C_ss 0.662 0.198 3.338 0.001 1.123 1.090
## C_fa 0.808 0.207 3.904 0.000 1.372 1.236
## C_ef 0.345 0.222 1.551 0.121 0.585 0.572
## C_ac 0.652 0.181 3.593 0.000 1.106 1.040
## C_wo -0.506 1.016 -0.497 0.619 -0.858 -0.963
## f1 =~
## W_phy 1.000 0.353 0.082
## C_as 3.454 8.905 0.388 0.698 1.220 1.149
## C_ss 1.024 2.647 0.387 0.699 0.362 0.351
## C_fa 1.800 4.587 0.392 0.695 0.636 0.573
## C_ac 1.378 3.535 0.390 0.697 0.487 0.458
## W_env -12.097 30.497 -0.397 0.692 -4.275 -0.969
## f2 =~
## W_psy 1.000 1.192 0.343
## C_ef 0.262 0.192 1.367 0.172 0.312 0.305
## C_wo 1.225 1.413 0.867 0.386 1.461 1.640
## W_soc 1.096 0.334 3.279 0.001 1.306 0.539
##
## Covariances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## f1 ~~
## f2 -0.342 0.609 -0.562 0.574 -0.812 -0.812
## WHOQ ~~
## CLDQ -3.870 2.358 -1.641 0.101 -0.795 -0.795
## f1 0.856 1.732 0.494 0.621 0.845 0.845
## f2 -2.569 2.251 -1.141 0.254 -0.751 -0.751
## CLDQ ~~
## f1 -0.545 1.144 -0.476 0.634 -0.909 -0.909
## f2 1.856 1.678 1.106 0.269 0.917 0.917
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .W_phy 8.298 0.955 8.688 0.000 8.298 0.452
## .W_psy 4.167 0.556 7.499 0.000 4.167 0.345
## .W_soc 2.974 0.368 8.092 0.000 2.974 0.506
## .W_env 1.064 4.897 0.217 0.828 1.064 0.055
## .C_as 0.523 0.117 4.477 0.000 0.523 0.463
## .C_ss 0.407 0.047 8.576 0.000 0.407 0.384
## .C_fa 0.531 0.062 8.527 0.000 0.531 0.431
## .C_ef 0.272 0.047 5.789 0.000 0.272 0.260
## .C_ac 0.650 0.067 9.721 0.000 0.650 0.575
## .C_wo 0.223 0.382 0.582 0.560 0.223 0.281
## WHOQ 8.228 3.900 2.110 0.035 1.000 1.000
## CLDQ 2.881 2.332 1.235 0.217 1.000 1.000
## f1 0.125 0.571 0.219 0.827 1.000 1.000
## f2 1.421 1.550 0.917 0.359 1.000 1.000兩問卷CFA(fit_M6畫圖)
semPaths(fit_M6, whatLabels='std', residual=F,
fixedStyle=c('black', lty=1),
freeStyle=c('black', lty=1),
egde.label.position=.4)## Warning in qgraph::qgraph(Edgelist, labels = nLab, bidirectional = Bidir, : The
## following arguments are not documented and likely not arguments of qgraph and
## thus ignored: egde.label.position
比較兩問卷差異
anova(fit_M1, fit_M2)## Warning in lavTestLRT(object = object, ..., model.names = NAMES): lavaan
## WARNING: some models are based on a different set of observed variables## Chi-Squared Difference Test
##
## Df AIC BIC Chisq Chisq diff Df diff Pr(>Chisq)
## fit_M1 2 4776.8 4804.7 2.1996
## fit_M2 9 3628.8 3670.6 14.2414 12.042 7 0.09919 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1