[1] "R version 3.4.2 (2017-09-28)"
R version 3.4.2 (2017-09-28)
Platform: x86_64-apple-darwin15.6.0 (64-bit)
Running under: macOS Sierra 10.12.6

Matrix products: default
BLAS: /System/Library/Frameworks/Accelerate.framework/Versions/A/Frameworks/vecLib.framework/Versions/A/libBLAS.dylib
LAPACK: /Library/Frameworks/R.framework/Versions/3.4/Resources/lib/libRlapack.dylib

locale:
[1] C

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods   base     

other attached packages:
 [1] coin_1.2-2      survival_2.41-3 outliers_0.14   lsr_0.5         dplyr_0.7.4    
 [6] ggpubr_0.1.5    magrittr_1.5    pwr_1.2-1       psych_1.7.8     MASS_7.3-47    
[11] lattice_0.20-35 reshape_0.8.7   ggplot2_2.2.1   car_2.1-5       foreign_0.8-69 
[16] nlme_3.1-131    r2glmm_0.1.2    lme4_1.1-14     Matrix_1.2-11  

loaded via a namespace (and not attached):
 [1] zoo_1.8-0          modeltools_0.2-21  splines_3.4.2      colorspace_1.3-2  
 [5] stats4_3.4.2       yaml_2.1.14        mgcv_1.8-20        rlang_0.1.2       
 [9] nloptr_1.0.4       glue_1.2.0         bindrcpp_0.2       multcomp_1.4-7    
[13] plyr_1.8.4         bindr_0.1          MatrixModels_0.4-1 munsell_0.4.3     
[17] gtable_0.2.0       mvtnorm_1.0-6      codetools_0.2-15   SparseM_1.77      
[21] quantreg_5.34      pbkrtest_0.4-7     parallel_3.4.2     TH.data_1.0-8     
[25] Rcpp_0.12.13       scales_0.5.0       mnormt_1.5-5       grid_3.4.2        
[29] tools_3.4.2        sandwich_2.4-0     lazyeval_0.2.1     tibble_1.3.4      
[33] pkgconfig_2.0.1    assertthat_0.2.0   minqa_1.2.4        R6_2.2.2          
[37] nnet_7.3-12        compiler_3.4.2    

###############################################################################

# Analysis for the paper for International Journal of Human-Computer Studies: Virtual reality negotiation training system with exposure to simulated thoughts and conversations: Design and evaluation

# 2018 TUDelft

# Output file: output_analysisII_MainResults.txt will be created 

# Author: Ding Ding 

# required datafile from Data preparation I&II

# - DemographyData.csv

# - NegoKnowledge_CodingSamples.csv

# - SE_With aLL sessions.csv

# - SE_CompareWL&EX.csv

# - SE_WL.csv

# - SE_EX.csv

# - SA_CompareWL&EX.csv

# - SA_WL.csv

# - SA_EX.csv

# - NegoF_CompareWL&EX.csv

# - NegoF_ALL.csv

# - NegoF_WL.csv

# - NegoF_EX.csv

# - NegoResult_CompareWL&EX.csv

# - NegoResult_ALL.csv

# - NegoResult_WL.csv

# - NegoResult_EX.csv

# - NegoKnowledge_CompareWL&EX.csv

# - NegoKnowledge_ALL.csv

# - NegoKnowledge_WL.csv

# - NegoKnowledge_EX.csv

# - Utility.csv

#################### Demographic data ####################

# File with all Demographic information of participants

# Data originally obtained from the file: DemographyData.csv

# data fields

# - ParticipantInfo

# - ParticipantInfoDirectWS: information of the participants joined the experiment directly as with self-motivation group

# - ParticipantInfoDirectWOS: information of the participants joined the experiment directly as without self-motivation group

# - ParticipantInfoDirectEX: information of the participants joined the experiment directly 

# - ParticipantInfoWL: information of the participants joined the waitinglist group 

# - ParticipantInfoInterventionWS: information of all the participants finally join the intervention  as with self-motivation group

# - ParticipantInfoInterventionWOS: information of all the participants finally join the intervention  as without self-motivation group

#################### refer to 4.1 Participants ####################
       ID           Gender        Age        VRexperience   Group   
 Min.   : 1.00   Female:17   Min.   :23.00   Maybe: 4     EWOS :12  
 1st Qu.:12.75   Male  :31   1st Qu.:25.75   No   :23     EWS  :12  
 Median :24.50               Median :27.00   Yes  :21     WLWOS:12  
 Mean   :24.50               Mean   :26.79                WLWS :12  
 3rd Qu.:36.25               3rd Qu.:28.00                          
 Max.   :48.00               Max.   :32.00                          
   vars  n  mean   sd median trimmed  mad min max range skew kurtosis   se
X1    1 48 26.79 2.04     27    26.7 1.48  23  32     9 0.41     0.15 0.29

#################### refer to 4.4.1 Data preparation ####################

###### refer to table 3:Demographic characteristics and pre-measurements ###### 

### Age ####

## Waitlist vs Training

# 1.Waitlist
   vars  n  mean   sd median trimmed  mad min max range skew kurtosis   se
X1    1 24 26.62 1.93     27    26.5 1.48  23  32     9 0.62     0.81 0.39

# 2.Training
   vars  n  mean   sd median trimmed  mad min max range skew kurtosis   se
X1    1 24 26.96 2.18     27    26.9 1.48  23  32     9  0.2    -0.47 0.44

Levene's test shows no sign difference between the group variance, therefore  Two Sample t-test conducted

	Two Sample t-test

data:  x by g
t = -0.56143, df = 46, p-value = 0.5772
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
 -1.5284341  0.8617674
sample estimates:
mean in group 1 mean in group 2 
       26.62500        26.95833 


## Training with self-motivation vs without self-motivation

# 1.Training with self-motivation
   vars  n  mean   sd median trimmed  mad min max range skew kurtosis   se
X1    1 24 27.21 1.56     27    27.1 1.48  24  32     8 0.92     2.13 0.32

# 2.Training without self-motivation
   vars  n  mean   sd median trimmed  mad min max range skew kurtosis   se
X1    1 24 26.38 2.39     26   26.25 2.97  23  32     9 0.54    -0.64 0.49

Levene's test shows sign difference between the group variance, therefore  Welch Two Sample t-test conducted

	Welch Two Sample t-test

data:  x by g
t = 1.4295, df = 39.563, p-value = 0.1607
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
 -0.3452483  2.0119150
sample estimates:
mean in group 1 mean in group 2 
       27.20833        26.37500 


### Gender ###

## Waitlist vs Training

# 1.Waitlist
# A tibble: 2 x 2
  Gender     n
  <fctr> <int>
1 Female     7
2   Male    17

# 2.Training
# A tibble: 2 x 2
  Gender     n
  <fctr> <int>
1 Female    10
2   Male    14

	Pearson's Chi-squared test

data:  gender_EXWL[c(2, 3)]
X-squared = 0.81973, df = 1, p-value = 0.3653


# Training with self-motivation vs without self-motivation

# 1.Training with self-motivation
# A tibble: 2 x 2
  Gender     n
  <fctr> <int>
1 Female     8
2   Male    16

# 2.Training without self-motivation
# A tibble: 2 x 2
  Gender     n
  <fctr> <int>
1 Female     9
2   Male    15

	Pearson's Chi-squared test

data:  gender_WSWOS[c(2, 3)]
X-squared = 0.091082, df = 1, p-value = 0.7628


### Virtual Reality Experience ###

## Waitlist vs Training

# 1.Waitlist
# A tibble: 3 x 2
  VRexperience     n
        <fctr> <int>
1        Maybe     2
2           No    13
3          Yes     9

# 2.Training
# A tibble: 3 x 2
  VRexperience     n
        <fctr> <int>
1        Maybe     2
2           No    10
3          Yes    12

	Pearson's Chi-squared test

data:  VR_WLEX[c(2, 3)]
X-squared = 0.81988, df = 2, p-value = 0.6637


## Training with self-motivation vs without self-motivation

# 1.Training with self-motivation
# A tibble: 3 x 2
  VRexperience     n
        <fctr> <int>
1        Maybe     2
2           No    10
3          Yes    12

# 2.Training without self-motivation
# A tibble: 3 x 2
  VRexperience     n
        <fctr> <int>
1        Maybe     2
2           No    13
3          Yes     9

	Pearson's Chi-squared test

data:  VR_WSWOS[c(2, 3)]
X-squared = 0.81988, df = 2, p-value = 0.6637


#################### Self-efficacy ####################

#################### Compare the self-efficacy data of participants between waitinglist and experiment group

# File with the self-efficacy data of waitinglist and experiment group

# Data originally obtained from the file SE_CompareWL&EX.csv

# data fields

#1 ID: Participants ID

#2 Group: waitinglist or experiment group

#3 Session: Pre or Post

#4 Score: the self-efficacy data

#################### Compare the self-efficacy data of participants of training with self-motivation and without self-motivation group

# File with the self-efficacy data of all training sessions

# Data originally obtained from the file SE_With aLL sessions.csv

# data fields

#1 SE:  Self-efficacy data measured before the training session (Pre-measurement data)

#2 SE1: Self-efficacy data measured after the first training session 

#3 SE2: Self-efficacy data measured after the second training session

#4 SE3: Self-efficacy data measured after the third training session (Post-measurement data)

#5 SE_follow: Self-efficacy data measured two weeks after all the training sessions (Follow-up measurement data)

################# Negotiation knowledge ################# 

# File with the negotiation knowledge of participants from waitinglist and training group

# Data originally obtained from the file NegoKnowledge_CompareWL&EX.csv

#1 ID: Participants ID

#2 Group: waitinglist or experiment group(with self-motivation or without self-motivation)

#3 Session: Pre or Post

#4 Score: the negotiation knowledge test data

## Compare the negotiation knowledge of participants from training with self-motivation and without self-motivation group

# Data originally obtained from the file NegoKnowledge_ALL.csv

#1 ID: Participants ID

#2 Pre: pre-measurement data

#3 Post: post-measurement data

#4 FollowUp: followUp-measurement data

#5 Group: with self-motivation or without self-motivation

################# Negotiation behaviour and performance #################

####### Negotiation Frequency ######

# File with the negotiation frequency data of participants from waitinglist and training group

# Data originally obtained from the file NegoF_CompareWL&EX.csv

#1 ID: Participants ID

#2 Group: waitinglist or experiment group(with self-motivation or without self-motivation)

#3 Session: Pre or Post

#4 Score: the negotiation Frequency data

## Compare waitinglist and training group

#################### Compare the negotiation frequency data of participants of training with self-motivation and without self-motivation group

# File with the negotiation frequency data of participants from both training with self-motivation and  without self-motivation group

# Data originally obtained from the file NegoF_ALL.csv

#1 ID: Participants ID

#2 Pre: pre-measurement data

#3 Post: post-measurement data

#4 FollowUp: followUp-measurement data

#5 Group: with self-motivation or without self-motivation

####### Negotiation satisfaction #######

# Compare negotiation satisfaction data of participants between waitinglist and training

# File with the negotiation frequency data of participants from both waitinglist or experiment group

# Data originally obtained from the file SA_CompareWL&EX.csv

#1 ID: Participants ID

#2 Group: waitinglist or experiment group (with self-motivation or without self-motivation)

#3 Session: Pre or Post

#4 Score: the negotiation satisfaction data

## Compare negotiation satisfaction data of participants between with self-motivation and without self-motivation

# File with the negotiation satisfaction data of participants from both training with self-motivation and  without self-motivation group

# Data originally obtained from the file SA_ALL.csv

#1 ID: Participants ID

#2 Pre: pre-measurement data

#3 Post: post-measurement data

#4 FollowUp: followUp-measurement data

#5 Group: with self-motivation or without self-motivation

################# Negotiation Result #################

# Compare negotiation result data of participants between waitinglist and training

#1 ID: Participants ID

#2 Group: Waitinglist or experiment group (with self-motivation or without self-motivation)

#3 Session: Pre or Post

#4 Score: the negotiation result data

## Compare negotiation result data of participants between without self-motivation and with self-motivation group

#1 ID: Participants ID

#2 Pre: pre-measurement data

#3 Post: post-measurement data

#4 FollowUp: followUp-measurement data

#5 Group: with self-motivation or without self-motivation

#################### Compare the pre-measurement data of participants between waitinglist and training group

#################### refer to 4.4.1 Data preparation ####################

###### refer to table 3:Demographic characteristics and pre-measurements ###### 

## Self-efficacy: Waitlist vs Training

# 1.Waitlist
   vars  n mean   sd median trimmed  mad min max range  skew kurtosis   se
X1    1 24 2.21 1.61      2     2.3 1.48  -1   5     6 -0.56    -0.37 0.33

# 2.Training
   vars  n mean  sd median trimmed  mad min max range skew kurtosis   se
X1    1 24 1.83 2.3    2.5    2.15 2.22  -4   4     8   -1     0.02 0.47

Levene's test shows no sign difference between the group variance, therefore  Two Sample t-test conducted

	Two Sample t-test

data:  x by g
t = 0.65435, df = 46, p-value = 0.5161
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
 -0.7785612  1.5285612
sample estimates:
mean in group 1 mean in group 2 
       2.208333        1.833333 


## Self-efficacy: Training with self-motivation vs without self-motivation

# 1.Training with self-motivation
   vars  n mean   sd median trimmed  mad min max range  skew kurtosis   se
X1    1 24 1.29 2.03      2     1.5 1.48  -4   4     8 -1.01     0.31 0.41

# 2.Training without self-motivation
   vars  n mean   sd median trimmed  mad min max range  skew kurtosis   se
X1    1 24    2 1.69    2.5     2.1 2.22  -1   4     5 -0.26    -1.39 0.35

Levene's test shows no sign difference between the group variance, therefore  Two Sample t-test conducted

	Two Sample t-test

data:  x by g
t = 1.3117, df = 46, p-value = 0.1961
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
 -0.3786139  1.7952805
sample estimates:
mean in group 1 mean in group 2 
       2.000000        1.291667 


## Negotiation knowledge: Waitlist vs Training

# 1.Waitlist
   vars  n  mean    sd median trimmed   mad min max range skew kurtosis   se
X1    1 24 22.17 12.29   17.5    21.3 13.34   7  49    42  0.6     -0.9 2.51

# 2.Training
   vars  n mean    sd median trimmed  mad min max range skew kurtosis   se
X1    1 24 23.5 11.62     23    23.2 12.6   2  51    49  0.2     -0.4 2.37

Levene's test shows no sign difference between the group variance, therefore  Two Sample t-test conducted

	Two Sample t-test

data:  x by g
t = 0.38626, df = 46, p-value = 0.7011
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
 -5.614936  8.281603
sample estimates:
mean in group 1 mean in group 2 
       23.50000        22.16667 


## Negotiation knowledge:Training with self-motivation vs without self-motivation

# 1.Training with self-motivation
   vars  n  mean    sd median trimmed  mad min max range  skew kurtosis   se
X1    1 24 22.88 10.45     22   23.15 9.64   2  41    39 -0.08     -0.8 2.13

# 1.Training without self-motivation
   vars  n  mean    sd median trimmed   mad min max range skew kurtosis   se
X1    1 24 22.04 12.01     21    21.2 13.34   7  51    44 0.52    -0.58 2.45

Levene's test shows no sign difference between the group variance, therefore  Two Sample t-test conducted

	Two Sample t-test

data:  x by g
t = 0.25643, df = 46, p-value = 0.7988
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
 -5.708063  7.374730
sample estimates:
mean in group 1 mean in group 2 
       22.87500        22.04167 


## Negotiation frequency: Waitlist vs Training

# 1.Waitlist
   vars  n mean    sd median trimmed  mad min max range skew kurtosis   se
X1    1 24 6.67 11.84    3.5    4.25 2.22   0  60    60 3.79    14.19 2.42

# 2.Training
   vars  n mean   sd median trimmed  mad min max range skew kurtosis   se
X1    1 24  7.5 8.23      5    5.75 3.71   0  34    34 2.15     3.91 1.68

	Exact Wilcoxon-Mann-Whitney Test

data:  v by g (NegoF_Experiment$Pre, NegoF_Waitinglist$Pre)
Z = 1.2466, p-value = 0.2166
alternative hypothesis: true mu is not equal to 0


# p value:[1] 0.2166404

# The standardised z statistic Z:[1] 1.246551

## Negotiation frequency: Training with self-motivation vs without self-motivation

# 1.Training with self-motivation
   vars  n mean   sd median trimmed  mad min max range skew kurtosis   se
X1    1 24 6.62 8.27      4     4.7 2.97   0  34    34 2.37     4.71 1.69

# 1.Training without self-motivation
   vars  n mean   sd median trimmed  mad min max range skew kurtosis   se
X1    1 24 5.04 3.14    4.5    4.75 2.22   1  13    12 0.87    -0.25 0.64

	Exact Wilcoxon-Mann-Whitney Test

data:  v by g (NegoF_AllWOS$Pre, NegoF_AllWS$Pre)
Z = 0.1247, p-value = 0.9058
alternative hypothesis: true mu is not equal to 0


# p value:[1] 0.905824

# The standardised z statistic Z:[1] 0.1247032

## Negotiation satisfaction: Waitlist vs Training

# 1.Waitlist
   vars  n mean  sd median trimmed  mad min max range skew kurtosis   se
X1    1 24 2.14 1.3   2.38    2.11 1.48   0   5     5 0.03    -0.86 0.27

# 2.Training
   vars  n mean   sd median trimmed  mad   min max range  skew kurtosis   se
X1    1 24 1.75 1.57   1.62    1.79 1.85 -1.25   4  5.25 -0.13    -1.25 0.32

	Exact Wilcoxon-Mann-Whitney Test

data:  v by g (SA_Experiment$Pre, SA_Waitinglist$Pre)
Z = -0.73401, p-value = 0.4696
alternative hypothesis: true mu is not equal to 0


# p value:[1] 0.4695926

# The standardised z statistic Z:[1] -0.7340123

## Negotiation satisfaction: Training with self-motivation vs without self-motivation

# 1.Training with self-motivation
   vars  n mean  sd median trimmed  mad   min max range skew kurtosis   se
X1    1 24 1.51 1.6      1     1.5 2.04 -1.25   4  5.25 0.08    -1.41 0.33

# 2.Training without self-motivation
   vars  n mean   sd median trimmed mad   min max range skew kurtosis   se
X1    1 24 1.96 1.24   1.62    1.96 1.3 -0.25   4  4.25 0.13    -1.18 0.25

	Exact Wilcoxon-Mann-Whitney Test

data:  v by g (SA_AllWOS$Pre, SA_AllWS$Pre)
Z = 1.0867, p-value = 0.2823
alternative hypothesis: true mu is not equal to 0


# p value:[1] 0.2822764

# The standardised z statistic Z:[1] 1.086728

## Negotiation Result: Waitlist vs Training

# 1.Waitlist
   vars  n mean   sd median trimmed  mad min max range  skew kurtosis   se
X1    1 24 0.75 0.23   0.78    0.78 0.18   0   1     1 -1.33     2.03 0.05

# 2.Training
   vars  n mean   sd median trimmed  mad  min max range  skew kurtosis   se
X1    1 23 0.71 0.25   0.75    0.73 0.22 0.02   1  0.98 -0.76     0.23 0.05

	Exact Wilcoxon-Mann-Whitney Test

data:  v by
	 g (NegoResult_Experiment$Pre, NegoResult_Waitinglist$Pre)
Z = -0.66476, p-value = 0.513
alternative hypothesis: true mu is not equal to 0


# p value:[1] 0.5130339

# The standardised z statistic Z:[1] -0.6647585

## Negotiation Result: Training with self-motivation vs without self-motivation

# 1.Training with self-motivation
   vars  n mean   sd median trimmed  mad  min max range  skew kurtosis   se
X1    1 23 0.64 0.28   0.75    0.67 0.24 0.01   1  0.99 -0.73    -0.37 0.06

# 1.Training without self-motivation
   vars  n mean   sd median trimmed  mad  min max range  skew kurtosis   se
X1    1 24 0.76 0.22   0.75    0.77 0.36 0.28   1  0.72 -0.34    -1.13 0.05

	Exact Wilcoxon-Mann-Whitney Test

data:  v by g (NegoResult_AllWOS$Pre, NegoResult_AllWS$Pre)
Z = 1.3895, p-value = 0.1678
alternative hypothesis: true mu is not equal to 0


# p value:[1] 0.167789

# The standardised z statistic Z:[1] 1.389492

#################### Inter-rater reliability coefficient

# File with the sample coding of negotiation knowledge video test from two coders

# Data orignally obtained from the file NegoKnowledge_CodingSamples.csv

# data fields

# - ID

# - CodeA

# - codeB

#################### refer to 4.4.1 Data preparation ####################

###### refer to Reliability analysis of the coding of the negotiation knowledge test  ###### 
       vars  n  mean    sd median trimmed   mad min max range  skew kurtosis   se
CoderA    1 28 31.21 16.24     32   31.42 17.79   0  59    59 -0.15    -1.05 3.07
CoderB    2 28 32.18 17.64     32   32.25 23.72   2  59    57  0.05    -1.31 3.33

Reliability analysis   
Call: alpha(x = CodingSamples_NegoKnowledge[2:3])

  raw_alpha std.alpha G6(smc) average_r S/N   ase mean sd
      0.97      0.97    0.95      0.95  36 0.011   32 17

 lower alpha upper     95% confidence boundaries
0.95 0.97 0.99 

 Reliability if an item is dropped:
       raw_alpha std.alpha G6(smc) average_r S/N alpha se
CoderA      0.95      0.95     0.9      0.95  NA       NA
CoderB      0.95      0.95     0.9      0.95  NA       NA

 Item statistics 
        n raw.r std.r r.cor r.drop mean sd
CoderA 28  0.99  0.99  0.96   0.95   31 16
CoderB 28  0.99  0.99  0.96   0.95   32 18

#################### Utility

# File with the utility data of the system from all participants

# Data orignally obtained from the file Utility.csv

# ID: Participants ID

# Q1-Q7: the rating score of each item

# Group: with self-motivation or without self-motivation

#################### refer to 4.4.1 Data preparation ####################

###### refer to Reliability analysis of the utility questionnaire  ###### 

Reliability analysis   
Call: alpha(x = Utility_Satisfaction[2:4])

  raw_alpha std.alpha G6(smc) average_r S/N   ase mean   sd
      0.68       0.7     0.7      0.44 2.4 0.084  5.2 0.95

 lower alpha upper     95% confidence boundaries
0.52 0.68 0.85 

 Reliability if an item is dropped:
   raw_alpha std.alpha G6(smc) average_r  S/N alpha se
Q1      0.45      0.46    0.30      0.30 0.84    0.157
Q2      0.39      0.40    0.25      0.25 0.66    0.171
Q3      0.87      0.88    0.78      0.78 7.16    0.036

 Item statistics 
    n raw.r std.r r.cor r.drop mean  sd
Q1 48  0.82  0.85  0.82   0.63  5.4 1.0
Q2 48  0.86  0.87  0.85   0.64  5.2 1.2
Q3 48  0.69  0.65  0.32   0.29  5.0 1.3

Non missing response frequency for each item
      1    2    3    4    5    6    7 miss
Q1 0.02 0.00 0.00 0.08 0.44 0.33 0.12    0
Q2 0.02 0.00 0.06 0.15 0.29 0.35 0.12    0
Q3 0.02 0.02 0.12 0.12 0.27 0.38 0.06    0

Reliability analysis   
Call: alpha(x = Utility_Effectiveness[2:5])

  raw_alpha std.alpha G6(smc) average_r S/N   ase mean sd
      0.83      0.83     0.8      0.55 4.9 0.039  5.3  1

 lower alpha upper     95% confidence boundaries
0.75 0.83 0.91 

 Reliability if an item is dropped:
   raw_alpha std.alpha G6(smc) average_r S/N alpha se
Q4      0.77      0.78    0.72      0.54 3.5    0.056
Q5      0.73      0.74    0.65      0.48 2.8    0.066
Q6      0.79      0.79    0.73      0.56 3.8    0.052
Q7      0.83      0.83    0.78      0.62 5.0    0.040

 Item statistics 
    n raw.r std.r r.cor r.drop mean  sd
Q4 48  0.83  0.83  0.75   0.68  5.0 1.2
Q5 48  0.89  0.88  0.85   0.76  5.4 1.4
Q6 48  0.79  0.81  0.72   0.65  5.5 1.1
Q7 48  0.75  0.75  0.60   0.55  5.4 1.3

Non missing response frequency for each item
      1    2    3    4    5    6    7 miss
Q4 0.00 0.04 0.06 0.23 0.27 0.31 0.08    0
Q5 0.04 0.00 0.06 0.06 0.27 0.38 0.19    0
Q6 0.00 0.02 0.04 0.04 0.38 0.35 0.17    0
Q7 0.00 0.04 0.02 0.15 0.25 0.33 0.21    0

# Cronbach's alpha showed acceptable levels of reliability for the two subscales of the utility
    questionnaire, the satisfaction of the system (α = 0.6831539 ) and usefulness of the system (α = 0.8294492 ), respectively.

#################### Compare the Pre-Post data of participants between waitinglist and training group

#################### refer to 5.1 Pre, post, and follow-up ####################

###### refer to table 4:Primary and secondary outcome measures comparison between pre and post measurement for the waitlist and training condition, and comparison between pre and post differences between the groups. ###### 

### Pre-Post of self-efficacy

## Waitlist vs Training

#  1. Waitlist

Levene's test shows no sign difference between the group variance, therefore  Two Sample t-test conducted

	Two Sample t-test

data:  x by g
t = -1.7286, df = 46, p-value = 0.09059
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
 -1.623362  0.123362
sample estimates:
mean in group 1 mean in group 2 
       1.458333        2.208333 


# The effect size:[1] 0.4283814

# 2. Training

Levene's test shows no sign difference between the group variance, therefore  Two Sample t-test conducted

	Two Sample t-test

data:  x by g
t = 2.0355, df = 46, p-value = 0.04758
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
 0.01297293 2.32036040
sample estimates:
mean in group 1 mean in group 2 
       3.000000        1.833333 


# The effect size:[1] 0.7144345

# 3. Waitlist Vs Training

Levene's test shows no sign difference between the group variance, therefore  Two Sample t-test conducted

	Two Sample t-test

data:  x by g
t = 3.922, df = 46, p-value = 0.0002906
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
 0.9329629 2.9003704
sample estimates:
mean in group 1 mean in group 2 
       1.166667       -0.750000 


# The effect size:[1] 1.132173

## Training with self-motivation VS without self-motivation

Levene's test shows sign difference between the group variance, therefore  Welch Two Sample t-test conducted

	Welch Two Sample t-test

data:  x by g
t = 4.0986, df = 38.749, p-value = 0.0002053
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
 0.6962915 2.0537085
sample estimates:
mean in group 1 mean in group 2 
          1.750           0.375 


# The effect size:[1] 1.183173

### Pre-Post of Negotiation knowledge

## Waitlist vs Training

# 1. Waitlist

Levene's test shows no sign difference between the group variance, therefore  Two Sample t-test conducted

	Two Sample t-test

data:  x by g
t = -0.22467, df = 46, p-value = 0.8232
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
 -7.469399  5.969399
sample estimates:
mean in group 1 mean in group 2 
       21.41667        22.16667 


# The effect size:[1] 0.07257162

# 2. Training

Levene's test shows no sign difference between the group variance, therefore  Two Sample t-test conducted

	Two Sample t-test

data:  x by g
t = 3.8722, df = 46, p-value = 0.0003391
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
  7.582563 24.000770
sample estimates:
mean in group 1 mean in group 2 
       39.29167        23.50000 


# The effect size:[1] 0.9549222

# 3. Waitlist Vs training

Levene's test shows sign difference between the group variance, therefore  Welch Two Sample t-test conducted

	Welch Two Sample t-test

data:  x by g
t = 4.1556, df = 38.588, p-value = 0.0001739
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
  8.487427 24.595906
sample estimates:
mean in group 1 mean in group 2 
       15.79167        -0.75000 


# The effect size:[1] 1.199615

## Training with self-motivation VS without self-motivation

Levene's test shows no sign difference between the group variance, therefore  Two Sample t-test conducted

	Two Sample t-test

data:  x by g
t = 0.21354, df = 46, p-value = 0.8319
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
 -8.777493 10.860826
sample estimates:
mean in group 1 mean in group 2 
       14.75000        13.70833 


# The effect size:[1] 0.06164318

### Pre-Post of Negotiation Frequency

## Waitlist vs Training

# 1. Waitinglist

# p value:[1] 0.693519

# The standardised z statistic Z:[1] -0.394084

# The effect size:[1] 0.05688113

# 2. Training

# p value:[1] 0.5446592

# The standardised z statistic Z:[1] -0.6057825

# The effect size:[1] 0.08743718

# 3. Waitlist Vs Training

	Exact Wilcoxon-Mann-Whitney Test

data:  v by
	 g (NegoF_ExperimentChange, NegoF_WaitinglistChange)
Z = 1.115, p-value = 0.2698
alternative hypothesis: true mu is not equal to 0


# p value:[1] 0.2698398

# The standardised z statistic Z:[1] 1.115047

# The effect size:[1] 0.1609431

## Training with self-motivation VS without self-motivation

	Exact Wilcoxon-Mann-Whitney Test

data:  v by g (NegoF_WOSChange, NegoF_WSChange)
Z = 1.646, p-value = 0.1012
alternative hypothesis: true mu is not equal to 0


# p value:[1] 0.1011831

# The standardised z statistic Z:[1] 1.64597

# The effect size:[1] 0.2375753

### Pre-Post of Negotiation satisfaction

## Waitlist vs Training

# 1. Waitlist

# p value:[1] 0.1771607

# The standardised z statistic Z:[1] -1.349549

# The effect size:[1] 0.1947906

# 2. Training

# p value:[1] 0.08171588

# The standardised z statistic Z:[1] -1.740816

# The effect size:[1] 0.2512651

# 3. Waitlist Vs Training

	Exact Wilcoxon-Mann-Whitney Test

data:  v by g (SA_ExperimentChange, SA_WaitinglistChange)
Z = 2.179, p-value = 0.02879
alternative hypothesis: true mu is not equal to 0


# p value:[1] 0.02878684

# The standardised z statistic Z:[1] 2.179043

# The effect size:[1] 0.3145177

## Training with self-motivation VS without self-motivation

	Exact Wilcoxon-Mann-Whitney Test

data:  v by g (SA_WOSChange, SA_WSChange)
Z = -2.6579, p-value = 0.007159
alternative hypothesis: true mu is not equal to 0


# p value:[1] 0.007158568

# The standardised z statistic Z:[1] -2.657861

# The effect size:[1] 0.3836292

### Pre-Post of Negotiation result

## Waitlist vs Training

# 1. Waitlist

# p value:[1] 0.4288537

# The standardised z statistic Z:[1] -0.7911548

# The effect size:[1] 0.1141934

# 2. Training

# p value:[1] 0.01951748

# The standardised z statistic Z:[1] -2.335497

# The effect size:[1] 0.3370999

# 3. Waitlist Vs Training

	Exact Wilcoxon-Mann-Whitney Test

data:  v by
	 g (NegoResult_ExperimentChange, NegoResult_WaitinglistChange)
Z = 2.0178, p-value = 0.04342
alternative hypothesis: true mu is not equal to 0


# p value:[1] 0.0434227

# The standardised z statistic Z:[1] 2.017754

# The effect size:[1] 0.2912377

## Training with self-motivation VS without self-motivation

	Exact Wilcoxon-Mann-Whitney Test

data:  v by g (NegoResult_WOSChange, NegoResult_WSChange)
Z = -2.6728, p-value = 0.006736
alternative hypothesis: true mu is not equal to 0


# p value:[1] 0.006736279

# The standardised z statistic Z:[1] -2.672847

# The effect size:[1] 0.3857923

#################### Compare the Pre-FollowUp data of participants for the training without self-motivation and training with self-motivation condition

#################### refer to 5.1 Pre, post, and follow-up ####################

###### refer to table 5: Primary and secondary outcome measures comparison between pre and follow-up measurement for the training without self-motivation and training with self-motivation condition, and comparison between pre and follow-up differences between the groups.###### 

### Pre-FollowUp of self-efficacy

## Training with self-motivation VS without self-motivation

# 1. Training without self-motivation

Levene's test shows no sign difference between the group variance, therefore  Two Sample t-test conducted

	Two Sample t-test

data:  x by g
t = 0.65858, df = 45, p-value = 0.5135
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
 -0.6264242  1.2351198
sample estimates:
mean in group 1 mean in group 2 
       2.304348        2.000000 


# The effect size:[1] 0.2569309

# 2. Training with self-motivation

Levene's test shows no sign difference between the group variance, therefore  Two Sample t-test conducted

	Two Sample t-test

data:  x by g
t = 2.2806, df = 46, p-value = 0.02725
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
 0.1418375 2.2748292
sample estimates:
mean in group 1 mean in group 2 
       2.500000        1.291667 


# The effect size:[1] 0.7483864

# 3. Training with self-motivation VS Training without self-motivation

Levene's test shows no sign difference between the group variance, therefore  Two Sample t-test conducted

	Two Sample t-test

data:  x by g
t = 2.1806, df = 45, p-value = 0.03448
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
 0.06902771 1.73894331
sample estimates:
mean in group 1 mean in group 2 
      1.2083333       0.3043478 


# The effect size:[1] 0.6362944

### Pre-FollowUp of Negotiation knowledge

## Training with self-motivation VS without self-motivation

# 1. Training without self-motivation

Levene's test shows no sign difference between the group variance, therefore  Two Sample t-test conducted

	Two Sample t-test

data:  x by g
t = 2.6891, df = 45, p-value = 0.01001
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
  2.859945 19.926287
sample estimates:
mean in group 1 mean in group 2 
       33.43478        22.04167 

[1] 1.011919

# 2. Training with self-motivation

Levene's test shows no sign difference between the group variance, therefore  Two Sample t-test conducted

	Two Sample t-test

data:  x by g
t = 2.2236, df = 46, p-value = 0.03113
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
  0.8251323 16.5915343
sample estimates:
mean in group 1 mean in group 2 
       31.58333        22.87500 

[1] 0.5194973

# 3. Training with self-motivation VS Training without self-motivation

Levene's test shows no sign difference between the group variance, therefore  Two Sample t-test conducted

	Two Sample t-test

data:  x by g
t = -0.70828, df = 45, p-value = 0.4824
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
 -11.482273   5.507635
sample estimates:
mean in group 1 mean in group 2 
       8.708333       11.695652 

[1] 0.206672

### Pre-FollowUp of Negotiation frequency 

## Training with self-motivation VS without self-motivation

# 1. Training without self-motivation

# p value:[1] 0.6919199

# The standardised z statistic Z:[1] -0.3962509

# The effect size:[1] 0.05719389

# 2. Training with self-motivation

# p value:[1] 0.2036594

# The standardised z statistic Z:[1] -1.271195

# The effect size:[1] 0.1834812

# 3. Training with self-motivation VS Training without self-motivation

	Exact Wilcoxon-Mann-Whitney Test

data:  v by
	 g (NegoF_WOSChange_follow, NegoF_WSChange_follow)
Z = 1.4689, p-value = 0.1445
alternative hypothesis: true mu is not equal to 0


# p value:[1] 0.1444993

# The standardised z statistic Z:[1] 1.468859

# The effect size:[1] 0.2120115

### Pre-FollowUp of Negotiation satisfaction

## Training with self-motivation VS without self-motivation
# 1. Training without self-motivation

# p value:[1] 0.5051117

# The standardised z statistic Z:[1] -0.6664685

# The effect size:[1] 0.09619644
# 2. Training with self-motivation

# p value:[1] 0.04483789

# The standardised z statistic Z:[1] -2.006172

# The effect size:[1] 0.289566
# 3. Training with self-motivation VS Training without self-motivation

	Exact Wilcoxon-Mann-Whitney Test

data:  v by g (SA_WOSChange_follow, SA_WSChange_follow)
Z = -2.07, p-value = 0.03812
alternative hypothesis: true mu is not equal to 0


# p value:[1] 0.03811603

# The standardised z statistic Z:[1] -2.07005

# The effect size:[1] 0.298786

### Pre-FollowUp of Negotiation result

## Training with self-motivation VS without self-motivation

# 1. Training without self-motivation

# p value:[1] 0.7362805

# The standardised z statistic Z:[1] -0.336783

# The effect size:[1] 0.04861045

# 2. Training with self-motivation

# p value:[1] 0.0201361

# The standardised z statistic Z:[1] -2.323802

# The effect size:[1] 0.3354119

# 3. Training with self-motivation VS Training without self-motivation

	Exact Wilcoxon-Mann-Whitney Test

data:  v by
	 g (NegoResult_WOSChange_follow, NegoResult_WSChange_follow)
Z = -2.0422, p-value = 0.04086
alternative hypothesis: true mu is not equal to 0


# p value:[1] 0.04085937

# The standardised z statistic Z:[1] -2.042182

# The effect size:[1] 0.2947636

#################### refer to 5.2 Training session ####################

###### Multilevel analysis of self-efficacy across the training sessions ######

###### refer to table 6: Multilevel analysis results of self-efficacy across the training sessions. ###### 
       Model df      AIC      BIC    logLik   Test   L.Ratio p-value
Model1     1  3 565.6663 575.4231 -279.8332                         
Model2     2  6 560.4689 579.9825 -274.2344 1 vs 2 11.197466  0.0107
Model3     3  7 562.2501 585.0160 -274.1251 2 vs 3  0.218731  0.6400
Model4     4 10 557.2056 589.7284 -268.6028 3 vs 4 11.044498  0.0115
       Model df      AIC      BIC    logLik   Test  L.Ratio p-value
Model2     1  6 560.4689 579.9825 -274.2344                        
Model4     2 10 557.2056 589.7284 -268.6028 1 vs 2 11.26323  0.0238
Approximate 95% confidence intervals

 Fixed effects:
               lower     est.    upper
(Intercept) 2.145883 2.500335 2.854788
attr(,"label")
[1] "Fixed effects:"

 Random Effects:
  Level: ID 
                   lower     est.    upper
sd((Intercept)) 0.943153 1.178369 1.472246

 Within-group standard error:
    lower      est.     upper 
0.6985730 0.7843902 0.8807497 
Linear mixed-effects model fit by maximum likelihood
 Data: SE_Intervetion 
       AIC      BIC    logLik
  560.4689 579.9825 -274.2344

Random effects:
 Formula: ~1 | ID
        (Intercept)  Residual
StdDev:    1.183562 0.7542253

Fixed effects: Score ~ Session 
                     Value Std.Error  DF   t-value p-value
(Intercept)      2.2500000 0.2047257 140 10.990314  0.0000
SessionSE2       0.3958333 0.1555935 140  2.544023  0.0120
SessionSE3       0.4583333 0.1555935 140  2.945711  0.0038
SessionSE_follow 0.1442347 0.1566604 140  0.920684  0.3588
 Correlation: 
                 (Intr) SssSE2 SssSE3
SessionSE2       -0.380              
SessionSE3       -0.380  0.500       
SessionSE_follow -0.377  0.497  0.497

Standardized Within-Group Residuals:
        Min          Q1         Med          Q3         Max 
-2.92715538 -0.51359219 -0.03688568  0.51994878  2.25074356 

Number of Observations: 191
Number of Groups: 48 

#################### refer to 5.3 Perceived utility ####################

#1 Satisfaction related utility
   vars  n mean   sd median trimmed  mad min  max range  skew kurtosis   se
X1    1 48 5.22 0.95   5.33    5.27 0.99   1 6.67  5.67 -1.56     5.69 0.14

	One Sample t-test

data:  Utility_Satisfaction$Score
t = 8.8257, df = 47, p-value = 1.537e-11
alternative hypothesis: true mean is not equal to 4
95 percent confidence interval:
 4.938265 5.492291
sample estimates:
mean of x 
 5.215278 


#1 Effectiveness related utility
   vars  n mean   sd median trimmed  mad  min max range  skew kurtosis   se
X1    1 48 5.33 1.02    5.5    5.42 0.74 1.75   7  5.25 -1.15     2.15 0.15

	One Sample t-test

data:  Utility_Effectiveness$Score
t = 9.0318, df = 47, p-value = 7.704e-12
alternative hypothesis: true mean is not equal to 4
95 percent confidence interval:
 5.036346 5.630321
sample estimates:
mean of x 
 5.333333 


#Compare the utility data of participants from training with self-motivation and without self-motivation.

Levene's test shows no sign difference between the group variance, therefore  Two Sample t-test conducted

	Two Sample t-test

data:  x by g
t = 1.1643, df = 46, p-value = 0.2503
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
 -0.2328136  0.8717025
sample estimates:
mean in group 1 mean in group 2 
       5.375000        5.055556 


Levene's test shows no sign difference between the group variance, therefore  Two Sample t-test conducted

	Two Sample t-test

data:  x by g
t = 0.41964, df = 46, p-value = 0.6767
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
 -0.4745942  0.7245942
sample estimates:
mean in group 1 mean in group 2 
       5.395833        5.270833 

