in this case, we will use the package of “seminr” and “readxl”. if the package is not install at your computer, firstly, we must instal the package with the following script –> install.packages(“seminR”) and install.packages(“readxl”)
library(seminr) #to generate SEM PLS
## Warning: package 'seminr' was built under R version 4.1.3
library(readxl) #to import the data from excel format
## Warning: package 'readxl' was built under R version 4.1.3
namafile <- read_excel("C:/Users/almo/Dropbox/portofolio/SEM PLS/data dasar.xlsx",
sheet = "dasar")
namafile_mm <- constructs(composite("X1",
multi_items("O",
c(1:9))),
composite("X2",
multi_items("S",
c(1:10))),
composite("Y",
multi_items("WB",
c(1:16))),
composite("X3",
multi_items("Y",
c(1:5))))
namafile_mm <-as.reflective(namafile_mm)
namafile_sm <- relationships(paths(from="X1",
to=c("X2","X3","Y")),
paths(from="X2",
to="Y"),
paths(from="X3",
to="Y"))
plot(namafile_sm)
namafile_PLS <- estimate_pls(data = namafile,
measurement_model = namafile_mm,
structural_model = namafile_sm)
## Generating the seminr model
## All 442 observations are valid.
model_summary <- summary(namafile_PLS)
model_summary
##
## Results from package seminr (2.3.2)
##
## Path Coefficients:
## X2 X3 Y
## R^2 0.697 0.372 1.585
## AdjR^2 0.697 0.371 1.589
## X1 0.835 0.610 -0.362
## X2 . . 0.029
## X3 . . 1.435
##
## Reliability:
## alpha rhoC AVE rhoA
## X1 0.814 0.818 0.337 0.826
## X2 0.775 0.778 0.275 0.805
## X3 0.626 0.636 0.267 0.656
## Y 0.802 0.775 0.201 0.829
##
## Alpha, rhoC, and rhoA should exceed 0.7 while AVE should exceed 0.5
plot(namafile_PLS)
test will be valid if the factor loading value > 0.5
model_summary$loadings
## X1 X2 X3 Y
## O1 0.436 0.000 0.000 0.000
## O2 0.501 0.000 0.000 0.000
## O3 0.680 0.000 0.000 0.000
## O4 0.657 0.000 0.000 0.000
## O5 0.550 0.000 0.000 0.000
## O6 0.497 0.000 0.000 0.000
## O7 0.594 0.000 0.000 0.000
## O8 0.656 0.000 0.000 0.000
## O9 0.607 0.000 0.000 0.000
## S1 0.000 0.654 0.000 0.000
## S2 0.000 0.610 0.000 0.000
## S3 0.000 0.333 0.000 0.000
## S4 0.000 0.471 0.000 0.000
## S5 0.000 0.584 0.000 0.000
## S6 0.000 0.667 0.000 0.000
## S7 0.000 0.497 0.000 0.000
## S8 0.000 0.490 0.000 0.000
## S9 0.000 0.170 -0.000 0.000
## S10 0.000 0.561 0.000 0.000
## WB1 0.000 0.000 0.000 0.360
## WB2 0.000 0.000 0.000 0.348
## WB3 0.000 0.000 0.000 0.331
## WB4 0.000 0.000 0.000 0.307
## WB5 0.000 0.000 0.000 0.307
## WB6 0.000 0.000 0.000 0.386
## WB7 0.000 0.000 0.000 0.227
## WB8 0.000 0.000 0.000 0.148
## WB9 0.000 0.000 0.000 0.443
## WB10 0.000 0.000 0.000 0.721
## WB11 0.000 0.000 0.000 0.456
## WB12 0.000 0.000 0.000 0.734
## WB13 0.000 0.000 0.000 0.519
## WB14 0.000 0.000 0.000 0.252
## WB15 0.000 0.000 0.000 0.374
## WB16 0.000 0.000 0.000 0.713
## Y1 0.000 0.000 0.326 0.000
## Y2 0.000 0.000 0.594 0.000
## Y3 0.000 0.000 0.578 0.000
## Y4 0.000 0.000 0.571 0.000
## Y5 0.000 0.000 0.463 0.000
the composite reliability test indicate based on 2 values: 1. AVE value > 0.5 2. rhoA value > 0.7
model_summary$reliability
## alpha rhoC AVE rhoA
## X1 0.814 0.818 0.337 0.826
## X2 0.775 0.778 0.275 0.805
## X3 0.626 0.636 0.267 0.656
## Y 0.802 0.775 0.201 0.829
##
## Alpha, rhoC, and rhoA should exceed 0.7 while AVE should exceed 0.5
the value will show the greatest value in each own variables
model_summary$validity$cross_loadings
## X1 X2 X3 Y
## O1 0.460 0.246 0.245 0.308
## O2 0.503 0.329 0.291 0.273
## O3 0.718 0.450 0.381 0.378
## O4 0.698 0.442 0.349 0.374
## O5 0.600 0.501 0.218 0.187
## O6 0.611 0.453 0.190 0.177
## O7 0.715 0.503 0.264 0.233
## O8 0.736 0.499 0.322 0.312
## O9 0.660 0.462 0.291 0.294
## S1 0.446 0.706 0.393 0.391
## S2 0.445 0.689 0.325 0.318
## S3 0.283 0.423 0.085 0.110
## S4 0.336 0.604 0.237 0.258
## S5 0.462 0.679 0.243 0.248
## S6 0.495 0.709 0.314 0.335
## S7 0.352 0.442 0.223 0.277
## S8 0.389 0.523 0.181 0.206
## S9 0.177 0.244 -0.027 0.004
## S10 0.493 0.660 0.161 0.158
## WB1 0.089 0.135 0.362 0.577
## WB2 0.195 0.221 0.342 0.542
## WB3 0.130 0.131 0.332 0.536
## WB4 0.183 0.199 0.302 0.466
## WB5 0.267 0.255 0.296 0.476
## WB6 0.293 0.316 0.373 0.515
## WB7 0.208 0.239 0.215 0.301
## WB8 0.174 0.141 0.141 0.268
## WB9 0.121 0.078 0.452 0.395
## WB10 0.391 0.411 0.712 0.635
## WB11 0.138 0.112 0.463 0.575
## WB12 0.249 0.222 0.742 0.674
## WB13 0.292 0.248 0.516 0.501
## WB14 0.283 0.370 0.230 0.259
## WB15 0.174 0.118 0.377 0.505
## WB16 0.330 0.260 0.717 0.643
## Y1 0.121 0.078 0.452 0.395
## Y2 0.391 0.411 0.712 0.635
## Y3 0.330 0.260 0.717 0.643
## Y4 0.249 0.222 0.742 0.674
## Y5 0.292 0.248 0.516 0.501
model_summary$validity$htmt
## X1 X2 X3 Y
## X1 . . . .
## X2 0.847 . . .
## X3 0.610 0.546 . .
## Y 0.546 0.547 1.153 .
VIF value must be greater than 0.2 and less than 5
model_summary$vif_antecedents
## X2 :
## X1
## .
##
## X3 :
## X1
## .
##
## Y :
## X1 X2 X3
## 2.001 1.906 1.280
model_summary$path
## X2 X3 Y
## R^2 0.697 0.372 1.585
## AdjR^2 0.697 0.371 1.589
## X1 0.835 0.610 -0.362
## X2 . . 0.029
## X3 . . 1.435
model_summary$fSquare
## X1 X2 X3 Y
## X1 0.000 2.305 0.592 -0.061
## X2 0.000 0.000 0.000 0.006
## X3 0.000 0.000 0.000 -2.026
## Y 0.000 0.000 0.000 0.000
boot_seminr_model <- bootstrap_model(seminr_model = namafile_PLS,
nboot = 1000,cores = 2,seed = NULL)
## Bootstrapping model using seminr...
## SEMinR Model successfully bootstrapped
hasil_akhir <- summary(boot_seminr_model)
hasil_akhir
##
## Results from Bootstrap resamples: 1000
##
## Bootstrapped Structural Paths:
## Original Est. Bootstrap Mean Bootstrap SD T Stat. 2.5% CI 97.5% CI
## X1 -> X2 0.835 0.840 0.031 27.046 0.782 0.899
## X1 -> X3 0.610 0.614 0.060 10.182 0.498 0.731
## X1 -> Y -0.362 -0.385 0.144 -2.513 -0.721 -0.139
## X2 -> Y 0.029 0.031 0.117 0.249 -0.195 0.259
## X3 -> Y 1.435 1.461 0.110 13.059 1.301 1.726
##
## Bootstrapped Weights:
## Original Est. Bootstrap Mean Bootstrap SD T Stat. 2.5% CI 97.5% CI
## O1 -> X1 0.130 0.129 0.021 6.202 0.086 0.168
## O2 -> X1 0.150 0.150 0.019 7.870 0.111 0.186
## O3 -> X1 0.204 0.202 0.014 14.057 0.173 0.230
## O4 -> X1 0.197 0.195 0.015 13.283 0.166 0.225
## O5 -> X1 0.164 0.166 0.022 7.485 0.122 0.207
## O6 -> X1 0.149 0.149 0.017 8.797 0.113 0.180
## O7 -> X1 0.178 0.178 0.014 12.663 0.151 0.205
## O8 -> X1 0.196 0.196 0.012 15.969 0.174 0.222
## O9 -> X1 0.182 0.180 0.014 12.892 0.154 0.208
## S1 -> X2 0.213 0.213 0.013 16.100 0.189 0.241
## S2 -> X2 0.199 0.198 0.014 14.196 0.172 0.227
## S3 -> X2 0.109 0.108 0.019 5.608 0.070 0.146
## S4 -> X2 0.154 0.153 0.019 8.057 0.114 0.188
## S5 -> X2 0.191 0.190 0.014 13.523 0.164 0.218
## S6 -> X2 0.218 0.217 0.014 15.068 0.191 0.247
## S7 -> X2 0.162 0.161 0.019 8.523 0.124 0.197
## S8 -> X2 0.160 0.158 0.016 9.753 0.125 0.191
## S9 -> X2 0.055 0.054 0.023 2.466 0.011 0.099
## S10 -> X2 0.183 0.183 0.017 10.699 0.151 0.218
## WB1 -> Y 0.102 0.101 0.010 10.413 0.082 0.120
## WB2 -> Y 0.099 0.097 0.011 9.007 0.075 0.117
## WB3 -> Y 0.094 0.093 0.014 6.843 0.062 0.118
## WB4 -> Y 0.087 0.086 0.014 6.084 0.053 0.111
## WB5 -> Y 0.087 0.086 0.012 6.944 0.059 0.109
## WB6 -> Y 0.109 0.109 0.012 8.878 0.085 0.132
## WB7 -> Y 0.064 0.064 0.013 4.842 0.035 0.089
## WB8 -> Y 0.042 0.041 0.015 2.763 0.009 0.069
## WB9 -> Y 0.125 0.125 0.024 5.325 0.077 0.169
## WB10 -> Y 0.204 0.203 0.017 11.842 0.172 0.237
## WB11 -> Y 0.129 0.129 0.012 10.700 0.106 0.153
## WB12 -> Y 0.208 0.207 0.018 11.703 0.176 0.247
## WB13 -> Y 0.147 0.146 0.016 9.160 0.114 0.175
## WB14 -> Y 0.071 0.072 0.016 4.401 0.043 0.106
## WB15 -> Y 0.106 0.105 0.011 9.409 0.083 0.128
## WB16 -> Y 0.202 0.202 0.017 11.658 0.171 0.238
## Y1 -> X3 0.198 0.197 0.036 5.567 0.125 0.260
## Y2 -> X3 0.360 0.358 0.021 17.373 0.320 0.397
## Y3 -> X3 0.351 0.351 0.020 17.150 0.311 0.393
## Y4 -> X3 0.347 0.347 0.021 16.880 0.309 0.392
## Y5 -> X3 0.281 0.279 0.026 10.803 0.225 0.331
##
## Bootstrapped Loadings:
## Original Est. Bootstrap Mean Bootstrap SD T Stat. 2.5% CI 97.5% CI
## O1 -> X1 0.436 0.430 0.071 6.098 0.289 0.566
## O2 -> X1 0.501 0.501 0.068 7.408 0.364 0.625
## O3 -> X1 0.680 0.674 0.046 14.903 0.581 0.759
## O4 -> X1 0.657 0.652 0.048 13.706 0.555 0.743
## O5 -> X1 0.550 0.552 0.074 7.422 0.397 0.687
## O6 -> X1 0.497 0.498 0.063 7.845 0.361 0.614
## O7 -> X1 0.594 0.594 0.046 12.980 0.495 0.675
## O8 -> X1 0.656 0.654 0.039 16.910 0.575 0.728
## O9 -> X1 0.607 0.602 0.048 12.773 0.504 0.686
## S1 -> X2 0.654 0.651 0.038 17.326 0.574 0.724
## S2 -> X2 0.610 0.608 0.042 14.375 0.527 0.688
## S3 -> X2 0.333 0.331 0.062 5.348 0.210 0.452
## S4 -> X2 0.471 0.470 0.066 7.167 0.333 0.592
## S5 -> X2 0.584 0.583 0.045 13.068 0.494 0.668
## S6 -> X2 0.667 0.664 0.038 17.446 0.585 0.738
## S7 -> X2 0.497 0.494 0.057 8.689 0.377 0.604
## S8 -> X2 0.490 0.485 0.053 9.199 0.372 0.581
## S9 -> X2 0.170 0.166 0.070 2.420 0.031 0.303
## S10 -> X2 0.561 0.560 0.054 10.343 0.450 0.660
## WB1 -> Y 0.360 0.359 0.050 7.271 0.256 0.454
## WB2 -> Y 0.348 0.345 0.055 6.272 0.242 0.446
## WB3 -> Y 0.331 0.332 0.066 5.033 0.201 0.465
## WB4 -> Y 0.307 0.306 0.064 4.806 0.176 0.430
## WB5 -> Y 0.307 0.308 0.058 5.283 0.189 0.421
## WB6 -> Y 0.386 0.386 0.056 6.865 0.274 0.488
## WB7 -> Y 0.227 0.227 0.054 4.166 0.122 0.333
## WB8 -> Y 0.148 0.149 0.061 2.432 0.028 0.266
## WB9 -> Y 0.443 0.440 0.079 5.627 0.273 0.575
## WB10 -> Y 0.721 0.716 0.037 19.414 0.641 0.781
## WB11 -> Y 0.456 0.455 0.046 9.862 0.359 0.542
## WB12 -> Y 0.734 0.732 0.036 20.593 0.659 0.796
## WB13 -> Y 0.519 0.516 0.061 8.500 0.378 0.619
## WB14 -> Y 0.252 0.254 0.046 5.466 0.166 0.342
## WB15 -> Y 0.374 0.372 0.053 7.069 0.270 0.475
## WB16 -> Y 0.713 0.711 0.037 19.131 0.635 0.777
## Y1 -> X3 0.326 0.327 0.066 4.950 0.195 0.447
## Y2 -> X3 0.594 0.591 0.040 14.689 0.509 0.669
## Y3 -> X3 0.578 0.580 0.039 14.647 0.500 0.656
## Y4 -> X3 0.571 0.572 0.039 14.531 0.490 0.643
## Y5 -> X3 0.463 0.462 0.051 9.000 0.352 0.553
##
## Bootstrapped HTMT:
## Original Est. Bootstrap Mean Bootstrap SD 2.5% CI 97.5% CI
## X1 -> X2 0.847 0.850 0.031 0.789 0.908
## X1 -> X3 0.610 0.617 0.056 0.515 0.726
## X1 -> Y 0.546 0.555 0.048 0.461 0.647
## X2 -> X3 0.546 0.570 0.052 0.474 0.674
## X2 -> Y 0.547 0.570 0.040 0.494 0.655
## X3 -> Y 1.153 1.157 0.036 1.095 1.229
##
## Bootstrapped Total Paths:
## Original Est. Bootstrap Mean Bootstrap SD 2.5% CI 97.5% CI
## X1 -> X2 0.835 0.840 0.031 0.782 0.899
## X1 -> X3 0.610 0.614 0.060 0.498 0.731
## X1 -> Y 0.538 0.542 0.058 0.422 0.651
## X2 -> Y 0.029 0.031 0.117 -0.195 0.259
## X3 -> Y 1.435 1.461 0.110 1.301 1.726
plot(boot_seminr_model)
specific_effect_significance(boot_seminr_model=boot_seminr_model,
from="X1",to="X2",alpha=0.05)
## Original Est. Bootstrap Mean Bootstrap SD T Stat. 2.5% CI
## 0.8351141 0.8404714 0.0308780 27.0456041 0.7822190
## 97.5% CI
## 0.8990292
specific_effect_significance(boot_seminr_model=boot_seminr_model,
from="X1",to="X3",alpha=0.05)
## Original Est. Bootstrap Mean Bootstrap SD T Stat. 2.5% CI
## 0.6099043 0.6143091 0.0598987 10.1822617 0.4980558
## 97.5% CI
## 0.7306332
specific_effect_significance(boot_seminr_model=boot_seminr_model,
from="X1",to="Y",alpha=0.05)
## Original Est. Bootstrap Mean Bootstrap SD T Stat. 2.5% CI
## -0.3619054 -0.3849562 0.1440009 -2.5132170 -0.7211649
## 97.5% CI
## -0.1386294
specific_effect_significance(boot_seminr_model=boot_seminr_model,
from="X2",to="Y",alpha=0.05)
## Original Est. Bootstrap Mean Bootstrap SD T Stat. 2.5% CI
## 0.02927162 0.03111142 0.11739573 0.24934146 -0.19495529
## 97.5% CI
## 0.25899488
specific_effect_significance(boot_seminr_model=boot_seminr_model,
from="X3",to="Y",alpha=0.05)
## Original Est. Bootstrap Mean Bootstrap SD T Stat. 2.5% CI
## 1.4346170 1.4607647 0.1098548 13.0592127 1.3010321
## 97.5% CI
## 1.7259090
specific_effect_significance(boot_seminr_model=boot_seminr_model,
from="X1",through="X2",
to="Y",alpha=0.05)
## Original Est. Bootstrap Mean Bootstrap SD T Stat. 2.5% CI
## 0.02444515 0.02630738 0.09996142 0.24454581 -0.16551964
## 97.5% CI
## 0.22367879
specific_effect_significance(boot_seminr_model=boot_seminr_model,
from="X1",through="X3",
to="Y",alpha=0.05)
## Original Est. Bootstrap Mean Bootstrap SD T Stat. 2.5% CI
## 0.8749790 0.9006687 0.1380564 6.3378353 0.6759174
## 97.5% CI
## 1.2149333