C-PU-PR Kalibrasi Item (skala Greed Avoidance)
Heru Wiryanto
September 2, 2017
Analisa Reliabilitas
Skala Greed Avoidance terdiri dari 9 item dengan normor : 119, 126, 132, 138, 144, 151, 157, 163, 169
Pembuktian reliabilitas dilakukan berdasarkan analisa koefisien internal konsistensi Alpha Cornbach dengan hasil analisa sebagai berikut
library(knitr)
library(CTT)
FULLDATA<-read.csv("~/Documents/MTPI ANALYSIS/CPU-PU-PR300.csv")
GAD<-FULLDATA[,c("i119", "i126", "i132", "i138", "i144", "i151", "i157", "i163", "i169")]
library(CTT)
reliability(GAD)##
## Number of Items
## 9
##
## Number of Examinees
## 300
##
## Coefficient Alpha
## 0.823responses<-GAD
#Item analysis
item.analysis <-
function(responses){
require(CTT, warn.conflicts = FALSE, quietly = TRUE)
(ctt.analysis <- CTT::reliability(responses, itemal = TRUE, NA.Delete = TRUE))
# Mark items that are potentially problematic
item.analysis <- data.frame(item.mean = ctt.analysis$itemMean,
alpha.del = ctt.analysis$alphaIfDeleted)
return(item.analysis)
}
dump("item.analysis", file = "item.analysis.R")
knitr::kable(item.analysis(responses),
align = "c",
caption = "Item Analysis")| item.mean | alpha.del | |
|---|---|---|
| i119 | 4.236667 | 0.8148740 |
| i126 | 4.066667 | 0.8095230 |
| i132 | 4.290000 | 0.8115936 |
| i138 | 4.753333 | 0.8094555 |
| i144 | 4.373333 | 0.7900109 |
| i151 | 4.546667 | 0.7961929 |
| i157 | 4.840000 | 0.8129773 |
| i163 | 5.070000 | 0.8018938 |
| i169 | 4.663333 | 0.7961115 |
Dari perhitungan di atas maka skala ini memiliki alpha cronbach sebesar 0.823 (Sangat Tinggi), dan pada tabel dibawahnya tidak satupun item dari skala GAD yang jika tidak diikutsertakan dapat menaikan nilai internal konsistensi maka semua item diikutsertakan.
Analisa Melalui Konfirmatory Analisa Factor (CFA)
KMO Bartleet
library(psych)##
## Attaching package: 'psych'## The following object is masked from 'package:CTT':
##
## polyseriallibrary(Hmisc)## Loading required package: lattice## Loading required package: survival## Loading required package: Formula## Loading required package: ggplot2##
## Attaching package: 'ggplot2'## The following objects are masked from 'package:psych':
##
## %+%, alpha##
## Attaching package: 'Hmisc'## The following object is masked from 'package:psych':
##
## describe## The following objects are masked from 'package:base':
##
## format.pval, round.POSIXt, trunc.POSIXt, unitsrGAD<-cor(GAD)
KMO(rGAD)## Kaiser-Meyer-Olkin factor adequacy
## Call: KMO(r = rGAD)
## Overall MSA = 0.84
## MSA for each item =
## i119 i126 i132 i138 i144 i151 i157 i163 i169
## 0.88 0.81 0.83 0.77 0.90 0.87 0.74 0.88 0.85Hasil perhitungan KMO Bartlet > 0.5 mengijinkan meneruskan analisa faktor dapat dilanjutkan dan nilai MSA tidak ada satupun yang nilainya <0.5 artinya semua item dapat dilibatkan dalam analisa faktor
CFA
library(lavaan)## This is lavaan 0.5-23.1097## lavaan is BETA software! Please report any bugs.##
## Attaching package: 'lavaan'## The following object is masked from 'package:psych':
##
## cor2covlibrary(semPlot)
library(knitr)
library(semTools)## ## ################################################################################# This is semTools 0.4-14## All users of R (or SEM) are invited to submit functions or ideas for functions.## #################################################################################
## Attaching package: 'semTools'## The following object is masked from 'package:psych':
##
## skew## The following object is masked from 'package:CTT':
##
## reliability#CFA
one.model = "GAD =~ i119 + i126 + i132 + i138 + i144 + i151 + i157 + i163 +i169"
#Run the model
one.fit = cfa(one.model,data = GAD)
semPaths(one.fit, whatLabels = "std", layout = "tree", intercepts = TRUE, residuals = TRUE)## Warning in qgraph(Edgelist, labels = nLab, bidirectional = Bidir, directed
## = Directed, : The following arguments are not documented and likely not
## arguments of qgraph and thus ignored: loopRotation; residuals; residScale;
## residEdge; CircleEdgeEnd
summary(one.fit, standardized = TRUE, fit.measures = T, rsquare = TRUE)## lavaan (0.5-23.1097) converged normally after 24 iterations
##
## Number of observations 300
##
## Estimator ML
## Minimum Function Test Statistic 155.439
## Degrees of freedom 27
## P-value (Chi-square) 0.000
##
## Model test baseline model:
##
## Minimum Function Test Statistic 803.541
## Degrees of freedom 36
## P-value 0.000
##
## User model versus baseline model:
##
## Comparative Fit Index (CFI) 0.833
## Tucker-Lewis Index (TLI) 0.777
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -3476.016
## Loglikelihood unrestricted model (H1) -3398.296
##
## Number of free parameters 18
## Akaike (AIC) 6988.031
## Bayesian (BIC) 7054.699
## Sample-size adjusted Bayesian (BIC) 6997.614
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.126
## 90 Percent Confidence Interval 0.107 0.145
## P-value RMSEA <= 0.05 0.000
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.076
##
## Parameter Estimates:
##
## Information Expected
## Standard Errors Standard
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## GAD =~
## i119 1.000 0.562 0.495
## i126 0.863 0.135 6.400 0.000 0.485 0.505
## i132 0.910 0.143 6.360 0.000 0.511 0.500
## i138 0.830 0.125 6.616 0.000 0.466 0.532
## i144 1.364 0.175 7.775 0.000 0.766 0.723
## i151 1.275 0.170 7.509 0.000 0.716 0.670
## i157 0.811 0.126 6.447 0.000 0.455 0.511
## i163 0.971 0.133 7.322 0.000 0.545 0.637
## i169 1.307 0.172 7.585 0.000 0.734 0.685
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .i119 0.972 0.085 11.483 0.000 0.972 0.755
## .i126 0.687 0.060 11.442 0.000 0.687 0.745
## .i132 0.785 0.068 11.463 0.000 0.785 0.750
## .i138 0.549 0.049 11.315 0.000 0.549 0.717
## .i144 0.534 0.055 9.638 0.000 0.534 0.477
## .i151 0.628 0.061 10.309 0.000 0.628 0.551
## .i157 0.587 0.051 11.416 0.000 0.587 0.739
## .i163 0.434 0.041 10.626 0.000 0.434 0.594
## .i169 0.611 0.060 10.152 0.000 0.611 0.531
## GAD 0.315 0.075 4.208 0.000 1.000 1.000
##
## R-Square:
## Estimate
## i119 0.245
## i126 0.255
## i132 0.250
## i138 0.283
## i144 0.523
## i151 0.449
## i157 0.261
## i163 0.406
## i169 0.469fitmeasures(one.fit)## npar fmin chisq
## 18.000 0.259 155.439
## df pvalue baseline.chisq
## 27.000 0.000 803.541
## baseline.df baseline.pvalue cfi
## 36.000 0.000 0.833
## tli nnfi rfi
## 0.777 0.777 0.742
## nfi pnfi ifi
## 0.807 0.605 0.835
## rni logl unrestricted.logl
## 0.833 -3476.016 -3398.296
## aic bic ntotal
## 6988.031 7054.699 300.000
## bic2 rmsea rmsea.ci.lower
## 6997.614 0.126 0.107
## rmsea.ci.upper rmsea.pvalue rmr
## 0.145 0.000 0.069
## rmr_nomean srmr srmr_bentler
## 0.069 0.076 0.076
## srmr_bentler_nomean srmr_bollen srmr_bollen_nomean
## 0.076 0.076 0.076
## srmr_mplus srmr_mplus_nomean cn_05
## 0.076 0.076 78.419
## cn_01 gfi agfi
## 91.639 0.897 0.828
## pgfi mfi ecvi
## 0.538 0.807 0.638summary(one.fit, fit.measures=TRUE)## lavaan (0.5-23.1097) converged normally after 24 iterations
##
## Number of observations 300
##
## Estimator ML
## Minimum Function Test Statistic 155.439
## Degrees of freedom 27
## P-value (Chi-square) 0.000
##
## Model test baseline model:
##
## Minimum Function Test Statistic 803.541
## Degrees of freedom 36
## P-value 0.000
##
## User model versus baseline model:
##
## Comparative Fit Index (CFI) 0.833
## Tucker-Lewis Index (TLI) 0.777
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -3476.016
## Loglikelihood unrestricted model (H1) -3398.296
##
## Number of free parameters 18
## Akaike (AIC) 6988.031
## Bayesian (BIC) 7054.699
## Sample-size adjusted Bayesian (BIC) 6997.614
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.126
## 90 Percent Confidence Interval 0.107 0.145
## P-value RMSEA <= 0.05 0.000
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.076
##
## Parameter Estimates:
##
## Information Expected
## Standard Errors Standard
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|)
## GAD =~
## i119 1.000
## i126 0.863 0.135 6.400 0.000
## i132 0.910 0.143 6.360 0.000
## i138 0.830 0.125 6.616 0.000
## i144 1.364 0.175 7.775 0.000
## i151 1.275 0.170 7.509 0.000
## i157 0.811 0.126 6.447 0.000
## i163 0.971 0.133 7.322 0.000
## i169 1.307 0.172 7.585 0.000
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .i119 0.972 0.085 11.483 0.000
## .i126 0.687 0.060 11.442 0.000
## .i132 0.785 0.068 11.463 0.000
## .i138 0.549 0.049 11.315 0.000
## .i144 0.534 0.055 9.638 0.000
## .i151 0.628 0.061 10.309 0.000
## .i157 0.587 0.051 11.416 0.000
## .i163 0.434 0.041 10.626 0.000
## .i169 0.611 0.060 10.152 0.000
## GAD 0.315 0.075 4.208 0.000parameterEstimates(one.fit, standardized=TRUE)## lhs op rhs est se z pvalue ci.lower ci.upper std.lv std.all
## 1 GAD =~ i119 1.000 0.000 NA NA 1.000 1.000 0.562 0.495
## 2 GAD =~ i126 0.863 0.135 6.400 0 0.599 1.128 0.485 0.505
## 3 GAD =~ i132 0.910 0.143 6.360 0 0.630 1.191 0.511 0.500
## 4 GAD =~ i138 0.830 0.125 6.616 0 0.584 1.075 0.466 0.532
## 5 GAD =~ i144 1.364 0.175 7.775 0 1.020 1.707 0.766 0.723
## 6 GAD =~ i151 1.275 0.170 7.509 0 0.943 1.608 0.716 0.670
## 7 GAD =~ i157 0.811 0.126 6.447 0 0.564 1.057 0.455 0.511
## 8 GAD =~ i163 0.971 0.133 7.322 0 0.711 1.231 0.545 0.637
## 9 GAD =~ i169 1.307 0.172 7.585 0 0.970 1.645 0.734 0.685
## 10 i119 ~~ i119 0.972 0.085 11.483 0 0.806 1.138 0.972 0.755
## 11 i126 ~~ i126 0.687 0.060 11.442 0 0.569 0.805 0.687 0.745
## 12 i132 ~~ i132 0.785 0.068 11.463 0 0.650 0.919 0.785 0.750
## 13 i138 ~~ i138 0.549 0.049 11.315 0 0.454 0.644 0.549 0.717
## 14 i144 ~~ i144 0.534 0.055 9.638 0 0.426 0.643 0.534 0.477
## 15 i151 ~~ i151 0.628 0.061 10.309 0 0.509 0.748 0.628 0.551
## 16 i157 ~~ i157 0.587 0.051 11.416 0 0.486 0.688 0.587 0.739
## 17 i163 ~~ i163 0.434 0.041 10.626 0 0.354 0.515 0.434 0.594
## 18 i169 ~~ i169 0.611 0.060 10.152 0 0.493 0.729 0.611 0.531
## 19 GAD ~~ GAD 0.315 0.075 4.208 0 0.168 0.462 1.000 1.000
## std.nox
## 1 0.495
## 2 0.505
## 3 0.500
## 4 0.532
## 5 0.723
## 6 0.670
## 7 0.511
## 8 0.637
## 9 0.685
## 10 0.755
## 11 0.745
## 12 0.750
## 13 0.717
## 14 0.477
## 15 0.551
## 16 0.739
## 17 0.594
## 18 0.531
## 19 1.000summary(one.fit, fit.measures=TRUE, standardized=TRUE)## lavaan (0.5-23.1097) converged normally after 24 iterations
##
## Number of observations 300
##
## Estimator ML
## Minimum Function Test Statistic 155.439
## Degrees of freedom 27
## P-value (Chi-square) 0.000
##
## Model test baseline model:
##
## Minimum Function Test Statistic 803.541
## Degrees of freedom 36
## P-value 0.000
##
## User model versus baseline model:
##
## Comparative Fit Index (CFI) 0.833
## Tucker-Lewis Index (TLI) 0.777
##
## Loglikelihood and Information Criteria:
##
## Loglikelihood user model (H0) -3476.016
## Loglikelihood unrestricted model (H1) -3398.296
##
## Number of free parameters 18
## Akaike (AIC) 6988.031
## Bayesian (BIC) 7054.699
## Sample-size adjusted Bayesian (BIC) 6997.614
##
## Root Mean Square Error of Approximation:
##
## RMSEA 0.126
## 90 Percent Confidence Interval 0.107 0.145
## P-value RMSEA <= 0.05 0.000
##
## Standardized Root Mean Square Residual:
##
## SRMR 0.076
##
## Parameter Estimates:
##
## Information Expected
## Standard Errors Standard
##
## Latent Variables:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## GAD =~
## i119 1.000 0.562 0.495
## i126 0.863 0.135 6.400 0.000 0.485 0.505
## i132 0.910 0.143 6.360 0.000 0.511 0.500
## i138 0.830 0.125 6.616 0.000 0.466 0.532
## i144 1.364 0.175 7.775 0.000 0.766 0.723
## i151 1.275 0.170 7.509 0.000 0.716 0.670
## i157 0.811 0.126 6.447 0.000 0.455 0.511
## i163 0.971 0.133 7.322 0.000 0.545 0.637
## i169 1.307 0.172 7.585 0.000 0.734 0.685
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## .i119 0.972 0.085 11.483 0.000 0.972 0.755
## .i126 0.687 0.060 11.442 0.000 0.687 0.745
## .i132 0.785 0.068 11.463 0.000 0.785 0.750
## .i138 0.549 0.049 11.315 0.000 0.549 0.717
## .i144 0.534 0.055 9.638 0.000 0.534 0.477
## .i151 0.628 0.061 10.309 0.000 0.628 0.551
## .i157 0.587 0.051 11.416 0.000 0.587 0.739
## .i163 0.434 0.041 10.626 0.000 0.434 0.594
## .i169 0.611 0.060 10.152 0.000 0.611 0.531
## GAD 0.315 0.075 4.208 0.000 1.000 1.000library(knitr)
library(dplyr) ##
## Attaching package: 'dplyr'## The following objects are masked from 'package:Hmisc':
##
## combine, src, summarize## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary(tidyr)
parameterEstimates(one.fit, standardized=TRUE) %>%
filter(op == "=~") %>%
select('Latent Factor'=lhs, Indicator=rhs, B=est, SE=se, Z=z, 'p-value'=pvalue, Beta=std.all) %>%
kable(digits = 3, format="pandoc", caption="Factor Loadings")| Latent Factor | Indicator | B | SE | Z | p-value | Beta |
|---|---|---|---|---|---|---|
| GAD | i119 | 1.000 | 0.000 | NA | NA | 0.495 |
| GAD | i126 | 0.863 | 0.135 | 6.400 | 0 | 0.505 |
| GAD | i132 | 0.910 | 0.143 | 6.360 | 0 | 0.500 |
| GAD | i138 | 0.830 | 0.125 | 6.616 | 0 | 0.532 |
| GAD | i144 | 1.364 | 0.175 | 7.775 | 0 | 0.723 |
| GAD | i151 | 1.275 | 0.170 | 7.509 | 0 | 0.670 |
| GAD | i157 | 0.811 | 0.126 | 6.447 | 0 | 0.511 |
| GAD | i163 | 0.971 | 0.133 | 7.322 | 0 | 0.637 |
| GAD | i169 | 1.307 | 0.172 | 7.585 | 0 | 0.685 |
Parameter CFA sudah memenuhi model fit
OMEGA
## Loading required namespace: GPArotation## Omega_h for 1 factor is not meaningful, just omega_t## Warning in schmid(m, nfactors, fm, digits, rotate = rotate, n.obs =
## n.obs, : Omega_h and Omega_asymptotic are not meaningful with one factor##
## Call: omegaSem(m = GAD, nfactors = 1, n.obs = 3277)
## Omega
## Call: omega(m = m, nfactors = nfactors, fm = fm, key = key, flip = flip,
## digits = digits, title = title, sl = sl, labels = labels,
## plot = plot, n.obs = n.obs, rotate = rotate, Phi = Phi, option = option)
## Alpha: 0.82
## G.6: 0.83
## Omega Hierarchical: 0.83
## Omega H asymptotic: 1
## Omega Total 0.83
##
## Schmid Leiman Factor loadings greater than 0.2
## g F1* h2 u2 p2
## i119 0.50 0.25 0.75 1
## i126 0.52 0.27 0.73 1
## i132 0.51 0.26 0.74 1
## i138 0.54 0.29 0.71 1
## i144 0.72 0.52 0.48 1
## i151 0.67 0.44 0.56 1
## i157 0.51 0.26 0.74 1
## i163 0.63 0.40 0.60 1
## i169 0.67 0.45 0.55 1
##
## With eigenvalues of:
## g F1*
## 3.1 0.0
##
## general/max 3.775284e+16 max/min = 1
## mean percent general = 1 with sd = 0 and cv of 0
## Explained Common Variance of the general factor = 1
##
## The degrees of freedom are 27 and the fit is 0.52
## The number of observations was 300 with Chi Square = 152.88 with prob < 1.5e-19
## The root mean square of the residuals is 0.08
## The df corrected root mean square of the residuals is 0.1
## RMSEA index = 0.126 and the 10 % confidence intervals are 0.106 0.144
## BIC = -1.13
##
## Compare this with the adequacy of just a general factor and no group factors
## The degrees of freedom for just the general factor are 27 and the fit is 0.52
## The number of observations was 300 with Chi Square = 152.88 with prob < 1.5e-19
## The root mean square of the residuals is 0.08
## The df corrected root mean square of the residuals is 0.1
##
## RMSEA index = 0.126 and the 10 % confidence intervals are 0.106 0.144
## BIC = -1.13
##
## Measures of factor score adequacy
## g F1*
## Correlation of scores with factors 0.92 0
## Multiple R square of scores with factors 0.84 0
## Minimum correlation of factor score estimates 0.68 -1
##
## Total, General and Subset omega for each subset
## g F1*
## Omega total for total scores and subscales 0.83 0.83
## Omega general for total scores and subscales 0.83 0.83
## Omega group for total scores and subscales 0.00 0.00
##
## The following analyses were done using the lavaan package
##
## With only 1 factor specified in the sem model, we can only calculate omega Total.
## You should probably rerun the sem specifying either a bifactor or hierarchical model.
##
## Omega Total from a confirmatory model using sem = 0.83
## With loadings of
## loads h2 u2 p2
## i119 0.49 0.24 0.76 1.00
## i126 0.50 0.25 0.75 1.00
## i132 0.50 0.25 0.75 1.00
## i138 0.53 0.28 0.72 1.00
## i144 0.72 0.52 0.48 1.00
## i151 0.67 0.45 0.55 1.00
## i157 0.51 0.26 0.74 1.00
## i163 0.64 0.40 0.60 1.02
## i169 0.68 0.47 0.53 0.98
##
## With eigenvalues of:
## loads
## 3.1
##
## The degrees of freedom of the confimatory model are 27 and the fit is 155.4388 with p = 0
## general/max NA max/min = NA
## mean percent general = 1 with sd = 0.01 and cv of 0.01
## Explained Common Variance of the general factor = 1
##
## To get the standard sem fit statistics, ask for summary on the fitted objectNilai Omega yang sangat tinggi diperoleh
KESIMPULAN
Untuk skala Greed Avoidance, semua item dapat digunakan dengan bobot sesuai eigen valuesnya, dan nilai reliabilitas skalanya sangat tinggi 0.823 yang dibuktikan dengan Alpha Cronbach, prinsip unidimensionalitasnya sudah terjaga dapat dibuktikan dengan hasil analisa faktor konfirmatorynya.