xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

Bachelor Thesis Katja Geierhaas

xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

Reference for PLS-Technique https://www.youtube.com/watch?v=Q-KiO2urNEU

Install Packages

Load Data

setwd("C:/Users/RIECK/Desktop/KatjaGeierhaas")
Katjadat<-read.csv("DatenKatja3.csv",sep=";")
head(Katjadat)
##   ResponseID Agreeableness HumanlikeDesign HedonicNature.1 HedonicNature.2
## 1          1             1               1               4               4
## 2          2             1               1               2               2
## 3          3             1               1               5               4
## 4          4             1               1               4               4
## 5          5             1               1               4               5
## 6          6             1               1               3               2
##   HedonicNature.3 PerceivedUsefulness.1 PerceivedUsefulness.2
## 1               4                     4                     4
## 2               2                     2                     3
## 3               4                     4                     4
## 4               4                     4                     4
## 5               3                     3                     4
## 6               3                     4                     4
##   PerceivedUsefulness.3 PerceivedUsefulness.4 PerceivedEaseofUse.1
## 1                     4                     5                    5
## 2                     2                     2                    4
## 3                     4                     5                    5
## 4                     4                     3                    4
## 5                     4                     5                    4
## 6                     3                     4                    4
##   PerceivedEaseofUse.2 BehavioralIntention.1 BehavioralIntention.2
## 1                    5                     5                     4
## 2                    3                     1                     1
## 3                    5                     5                     5
## 4                    4                     3                     3
## 5                    4                     3                     3
## 6                    5                     2                     2
##   BehavioralIntention.3 ActualUsage.1 ActualUsage.2 ActUsageHowOften
## 1                     3           0.1         -16.6                3
## 2                     1           0.1          -1.0                3
## 3                     5           7.1           0.0                6
## 4                     3           0.0         -16.6                1
## 5                     2           0.1          -5.2                3
## 6                     1           0.1         -16.6                2
##   ActualUsageWhenLast
## 1                   4
## 2                   2
## 3                   1
## 4                   4
## 5                   3
## 6                   4

xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

Model Analysis

(1) Factor Analysis

(2) PLS-Regression

We estimate 4 different Model Specifications

xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

Define PLS model structure

AGR<-c(0,0,0,0,0,0,0)
HD<-c(0,0,0,0,0,0,0)
HN<-c(0,1,0,0,0,0,0)
PEOU<-c(0,0,1,0,0,0,0)
PU<-c(1,0,1,1,0,0,0)
BI<-c(0,0,0,1,1,0,0)
AU<-c(0,0,0,0,0,1,0)

Path<-rbind(AGR,HD,HN,PEOU,PU,BI,AU)
KatjaBlocks<-list(2,3,4:6,11:12,7:10,13:15,18)
KatjaModes<-rep("A",7)
innerplot(Path)

PLS_Katjadat

factanal(Katjadat[,2:15],factors=6, rotation="varimax")
## 
## Call:
## factanal(x = Katjadat[, 2:15], factors = 6, rotation = "varimax")
## 
## Uniquenesses:
##         Agreeableness       HumanlikeDesign       HedonicNature.1 
##                 0.953                 0.931                 0.220 
##       HedonicNature.2       HedonicNature.3 PerceivedUsefulness.1 
##                 0.229                 0.219                 0.261 
## PerceivedUsefulness.2 PerceivedUsefulness.3 PerceivedUsefulness.4 
##                 0.005                 0.261                 0.458 
##  PerceivedEaseofUse.1  PerceivedEaseofUse.2 BehavioralIntention.1 
##                 0.445                 0.005                 0.184 
## BehavioralIntention.2 BehavioralIntention.3 
##                 0.097                 0.198 
## 
## Loadings:
##                       Factor1 Factor2 Factor3 Factor4 Factor5 Factor6
## Agreeableness                                          0.211         
## HumanlikeDesign                                                0.261 
## HedonicNature.1        0.407   0.367   0.660   0.107   0.176         
## HedonicNature.2        0.197   0.229   0.789                   0.219 
## HedonicNature.3        0.306   0.252   0.768           0.180         
## PerceivedUsefulness.1  0.796   0.219   0.165   0.129          -0.100 
## PerceivedUsefulness.2  0.652   0.151           0.733                 
## PerceivedUsefulness.3  0.707   0.227   0.354          -0.140  -0.202 
## PerceivedUsefulness.4  0.593   0.245   0.230   0.242  -0.125         
## PerceivedEaseofUse.1   0.680           0.201           0.172   0.119 
## PerceivedEaseofUse.2   0.715   0.206   0.192           0.526   0.353 
## BehavioralIntention.1  0.263   0.791   0.240   0.138   0.181  -0.107 
## BehavioralIntention.2  0.190   0.855   0.271           0.228         
## BehavioralIntention.3  0.169   0.810   0.196          -0.199   0.198 
## 
##                Factor1 Factor2 Factor3 Factor4 Factor5 Factor6
## SS loadings      3.314   2.494   2.111   0.656   0.588   0.373
## Proportion Var   0.237   0.178   0.151   0.047   0.042   0.027
## Cumulative Var   0.237   0.415   0.566   0.612   0.654   0.681
## 
## Test of the hypothesis that 6 factors are sufficient.
## The chi square statistic is 9.03 on 22 degrees of freedom.
## The p-value is 0.993
KatjaPLS<-plspm(Katjadat[1:116,],Path,KatjaBlocks,mode=KatjaModes)

KatjaPLS
## Partial Least Squares Path Modeling (PLS-PM) 
## ---------------------------------------------
##    NAME             DESCRIPTION
## 1  $outer_model     outer model
## 2  $inner_model     inner model
## 3  $path_coefs      path coefficients matrix
## 4  $scores          latent variable scores
## 5  $crossloadings   cross-loadings
## 6  $inner_summary   summary inner model
## 7  $effects         total effects
## 8  $unidim          unidimensionality
## 9  $gof             goodness-of-fit
## 10 $boot            bootstrap results
## 11 $data            data matrix
## ---------------------------------------------
## You can also use the function 'summary'
KatjaPLS$unidim
##      Mode MVs   C.alpha    DG.rho  eig.1st   eig.2nd
## AGR     A   1 1.0000000 1.0000000 1.000000 0.0000000
## HD      A   1 1.0000000 1.0000000 1.000000 0.0000000
## HN      A   3 0.8913512 0.9325031 2.464853 0.3088569
## PEOU    A   2 0.8010042 0.9095061 1.668063 0.3319374
## PU      A   4 0.8667299 0.9092258 2.858940 0.4766369
## BI      A   3 0.8978088 0.9365010 2.493395 0.3559977
## AU      A   1 1.0000000 1.0000000 1.000000 0.0000000
KatjaPLS$crossloadings
##                     name block          AGR            HD          HN
## 1          Agreeableness   AGR  1.000000000  0.000000e+00  0.06393359
## 2        HumanlikeDesign    HD  0.000000000  1.000000e+00  0.04404191
## 3        HedonicNature.1    HN  0.033786869  3.378687e-02  0.91555902
## 4        HedonicNature.2    HN  0.065653216  8.206652e-02  0.88291395
## 5        HedonicNature.3    HN  0.079416230  8.824026e-03  0.91871271
## 6   PerceivedEaseofUse.1  PEOU -0.009793103 -9.793103e-03  0.45909750
## 7   PerceivedEaseofUse.2  PEOU  0.111436418  9.286368e-02  0.57338694
## 8  PerceivedUsefulness.1    PU -0.019660827 -3.932165e-02  0.46933045
## 9  PerceivedUsefulness.2    PU  0.009085279  9.085279e-03  0.39906915
## 10 PerceivedUsefulness.3    PU  0.017444809 -1.744481e-02  0.56715994
## 11 PerceivedUsefulness.4    PU -0.022186946  7.395649e-03  0.46166306
## 12 BehavioralIntention.1    BI  0.046110212 -3.416172e-18  0.56965863
## 13 BehavioralIntention.2    BI  0.085021337 -3.864606e-02  0.58979325
## 14 BehavioralIntention.3    BI -0.030997509  6.199502e-02  0.45486686
## 15      ActUsageHowOften    AU -0.005617357  1.685207e-02 -0.11447555
##           PEOU           PU          BI           AU
## 1   0.06092753 -0.004598484 0.037894980 -0.005617357
## 2   0.04995144 -0.013199578 0.007632852  0.016852071
## 3   0.56366755  0.609450196 0.620080516 -0.068894825
## 4   0.44059236  0.413077609 0.461594310 -0.096256162
## 5   0.53143555  0.487555659 0.509137645 -0.151726736
## 6   0.89812028  0.613948530 0.289952696 -0.057046775
## 7   0.92722067  0.589975738 0.437047430 -0.064371419
## 8   0.61673994  0.879976866 0.425090795 -0.100833442
## 9   0.55639594  0.824802211 0.364592836 -0.144072535
## 10  0.54432931  0.852808488 0.452615448 -0.130919611
## 11  0.50467751  0.822097973 0.425467389  0.007104024
## 12  0.41485571  0.512077907 0.933549041  0.217143025
## 13  0.40403652  0.432365974 0.936004569  0.106416895
## 14  0.27631188  0.396875064 0.862807363  0.253089341
## 15 -0.06675431 -0.109102779 0.212090029  1.000000000
KatjaPLS$inner_model
## $HN
##                Estimate Std. Error       t value  Pr(>|t|)
## Intercept -5.063283e-17  0.0935677 -5.411357e-16 1.0000000
## HD         4.404191e-02  0.0935677  4.706957e-01 0.6387575
## 
## $PEOU
##               Estimate Std. Error      t value     Pr(>|t|)
## Intercept 2.767704e-16 0.07695879 3.596346e-15 1.000000e+00
## HN        5.699275e-01 0.07695879 7.405619e+00 2.433672e-11
## 
## $PU
##                Estimate Std. Error       t value     Pr(>|t|)
## Intercept -1.192806e-16 0.06757098 -1.765265e-15 1.000000e+00
## AGR       -5.313892e-02 0.06773972 -7.844574e-01 4.344278e-01
## HN         2.832323e-01 0.08228585  3.442054e+00 8.125678e-04
## PEOU       4.994849e-01 0.08227035  6.071263e+00 1.774896e-08
## 
## $BI
##                Estimate Std. Error       t value     Pr(>|t|)
## Intercept -9.520752e-18  0.0811460 -1.173287e-16 1.0000000000
## PEOU       1.386430e-01  0.1077197  1.287071e+00 0.2006995812
## PU         4.038179e-01  0.1077197  3.748784e+00 0.0002817625
## 
## $AU
##               Estimate Std. Error      t value   Pr(>|t|)
## Intercept 1.090173e-16 0.09152786 1.191083e-15 1.00000000
## BI        2.120900e-01 0.09152786 2.317218e+00 0.02227715
KatjaPLS$outer_model
##                     name block    weight   loading communality  redundancy
## 1          Agreeableness   AGR 1.0000000 1.0000000   1.0000000 0.000000000
## 2        HumanlikeDesign    HD 1.0000000 1.0000000   1.0000000 0.000000000
## 3        HedonicNature.1    HN 0.4197297 0.9155590   0.8382483 0.001625942
## 4        HedonicNature.2    HN 0.3254243 0.8829139   0.7795370 0.001512060
## 5        HedonicNature.3    HN 0.3574469 0.9187127   0.8440330 0.001637162
## 6   PerceivedEaseofUse.1  PEOU 0.5033099 0.8981203   0.8066200 0.262004169
## 7   PerceivedEaseofUse.2  PEOU 0.5909782 0.9272207   0.8597382 0.279257863
## 8  PerceivedUsefulness.1    PU 0.3117871 0.8799769   0.7743593 0.378372280
## 9  PerceivedUsefulness.2    PU 0.2670094 0.8248022   0.6802987 0.332411802
## 10 PerceivedUsefulness.3    PU 0.3150132 0.8528085   0.7272823 0.355369237
## 11 PerceivedUsefulness.4    PU 0.2879933 0.8220980   0.6758451 0.330235651
## 12 BehavioralIntention.1    BI 0.4160685 0.9335490   0.8715138 0.223048271
## 13 BehavioralIntention.2    BI 0.3428764 0.9360046   0.8761046 0.224223189
## 14 BehavioralIntention.3    BI 0.3368606 0.8628074   0.7444365 0.190525133
## 15      ActUsageHowOften    AU 1.0000000 1.0000000   1.0000000 0.044982180
KatjaPLS$path_coefs
##              AGR         HD        HN      PEOU        PU      BI AU
## AGR   0.00000000 0.00000000 0.0000000 0.0000000 0.0000000 0.00000  0
## HD    0.00000000 0.00000000 0.0000000 0.0000000 0.0000000 0.00000  0
## HN    0.00000000 0.04404191 0.0000000 0.0000000 0.0000000 0.00000  0
## PEOU  0.00000000 0.00000000 0.5699275 0.0000000 0.0000000 0.00000  0
## PU   -0.05313892 0.00000000 0.2832323 0.4994849 0.0000000 0.00000  0
## BI    0.00000000 0.00000000 0.0000000 0.1386430 0.4038179 0.00000  0
## AU    0.00000000 0.00000000 0.0000000 0.0000000 0.0000000 0.21209  0
KatjaPLS$gof
## [1] 0.4199263
KatjaPLS$effects
##    relationships      direct     indirect        total
## 1      AGR -> HD  0.00000000  0.000000000  0.000000000
## 2      AGR -> HN  0.00000000  0.000000000  0.000000000
## 3    AGR -> PEOU  0.00000000  0.000000000  0.000000000
## 4      AGR -> PU -0.05313892  0.000000000 -0.053138922
## 5      AGR -> BI  0.00000000 -0.021458450 -0.021458450
## 6      AGR -> AU  0.00000000 -0.004551123 -0.004551123
## 7       HD -> HN  0.04404191  0.000000000  0.044041911
## 8     HD -> PEOU  0.00000000  0.025100696  0.025100696
## 9       HD -> PU  0.00000000  0.025011511  0.025011511
## 10      HD -> BI  0.00000000  0.013580131  0.013580131
## 11      HD -> AU  0.00000000  0.002880210  0.002880210
## 12    HN -> PEOU  0.56992748  0.000000000  0.569927482
## 13      HN -> PU  0.28323232  0.284670168  0.567902484
## 14      HN -> BI  0.00000000  0.308345639  0.308345639
## 15      HN -> AU  0.00000000  0.065397035  0.065397035
## 16    PEOU -> PU  0.49948489  0.000000000  0.499484894
## 17    PEOU -> BI  0.13864295  0.201700959  0.340343914
## 18    PEOU -> AU  0.00000000  0.072183550  0.072183550
## 19      PU -> BI  0.40381794  0.000000000  0.403817936
## 20      PU -> AU  0.00000000  0.085645758  0.085645758
## 21      BI -> AU  0.21209003  0.000000000  0.212090029
KatjaPLS$inner_summary
##            Type         R2 Block_Communality Mean_Redundancy       AVE
## AGR   Exogenous 0.00000000         1.0000000     0.000000000 1.0000000
## HD    Exogenous 0.00000000         1.0000000     0.000000000 1.0000000
## HN   Endogenous 0.00193969         0.8206061     0.001591721 0.8206061
## PEOU Endogenous 0.32481733         0.8331791     0.270631016 0.8331791
## PU   Endogenous 0.48862626         0.7144463     0.349097242 0.7144463
## BI   Endogenous 0.25593200         0.8306850     0.212598864 0.8306850
## AU   Endogenous 0.04498218         1.0000000     0.044982180 1.0000000
plot(KatjaPLS)

End of Analysis