Determinants of bus users’ loyalty - LOY continuous
Phương Anh
20/03/2021
1. Read Data
# Read Data directly
t = "F:/NGHIEN CUU SINH/NCS - PHUONG ANH/Part 2-Satisfaction and Loyalty/So lieu/So lieu - PA xu ly/873_Loyaltyofbuspassenger_PAcode_NonBus_Mising data_outliers_forMLM_Analyse.csv"
DataLOY = read.csv(t, header = T)
head(DataLOY)## ID AGE CITY FRE TripPurpose Departure TimeUseonBus TravelTime PSSW PSSS PSAB
## 1 3 1 2 1 5 0 4 3.00 4.9 5.4 5.5
## 2 4 1 2 2 7 0 4 2.00 3.4 2.4 3.5
## 3 5 1 2 1 5 1 4 0.17 3.9 3.4 4.5
## 4 6 1 2 1 5 1 1 4.00 4.1 4.4 5.5
## 5 7 1 2 1 5 1 4 2.00 3.7 2.6 3.5
## 6 8 1 2 1 5 1 6 2.00 4.6 2.7 3.8
## PSEB PSQ SAT LOY IMA PHB PEV ATM PPI SIM PPA SBE EXB EC_Stop WC_Stop EC_Bus
## 1 5.8 4.8 6.0 5.7 5.6 6.6 4.0 4.3 6.0 3.5 4.5 4.0 4.8 2 1 2
## 2 6.0 4.6 4.7 4.3 4.8 4.0 5.3 4.1 4.0 4.0 4.0 4.8 4.2 2 2 1
## 3 4.5 2.7 2.0 3.7 3.0 5.0 5.8 3.1 2.7 3.5 4.5 6.0 4.0 2 2 2
## 4 6.0 4.8 5.0 5.0 5.0 5.0 5.0 5.0 5.0 5.0 5.0 5.0 5.0 2 1 2
## 5 4.5 4.5 4.0 4.6 4.6 5.6 6.0 3.3 3.0 5.5 5.0 5.0 4.2 2 1 2
## 6 4.0 3.9 4.7 4.4 3.0 5.4 5.3 2.7 3.0 2.0 2.5 2.0 5.0 2 1 2
## WC_Bus Gender MarriedStatus Occupation Education Income
## 1 1 2 1 1 2 1
## 2 2 2 1 1 2 1
## 3 2 1 1 1 2 1
## 4 1 1 1 1 2 1
## 5 1 1 1 1 2 1
## 6 1 2 1 1 3 1names(DataLOY)## [1] "ID" "AGE" "CITY" "FRE"
## [5] "TripPurpose" "Departure" "TimeUseonBus" "TravelTime"
## [9] "PSSW" "PSSS" "PSAB" "PSEB"
## [13] "PSQ" "SAT" "LOY" "IMA"
## [17] "PHB" "PEV" "ATM" "PPI"
## [21] "SIM" "PPA" "SBE" "EXB"
## [25] "EC_Stop" "WC_Stop" "EC_Bus" "WC_Bus"
## [29] "Gender" "MarriedStatus" "Occupation" "Education"
## [33] "Income"dim(DataLOY)## [1] 873 332. Desscriptive statistic
# 2.2. Change type of LOY, SAT and other factor variables
head(DataLOY)## ID AGE CITY FRE TripPurpose Departure TimeUseonBus TravelTime PSSW PSSS PSAB
## 1 3 1 2 1 5 0 4 3.00 4.9 5.4 5.5
## 2 4 1 2 2 7 0 4 2.00 3.4 2.4 3.5
## 3 5 1 2 1 5 1 4 0.17 3.9 3.4 4.5
## 4 6 1 2 1 5 1 1 4.00 4.1 4.4 5.5
## 5 7 1 2 1 5 1 4 2.00 3.7 2.6 3.5
## 6 8 1 2 1 5 1 6 2.00 4.6 2.7 3.8
## PSEB PSQ SAT LOY IMA PHB PEV ATM PPI SIM PPA SBE EXB EC_Stop WC_Stop EC_Bus
## 1 5.8 4.8 6.0 5.7 5.6 6.6 4.0 4.3 6.0 3.5 4.5 4.0 4.8 2 1 2
## 2 6.0 4.6 4.7 4.3 4.8 4.0 5.3 4.1 4.0 4.0 4.0 4.8 4.2 2 2 1
## 3 4.5 2.7 2.0 3.7 3.0 5.0 5.8 3.1 2.7 3.5 4.5 6.0 4.0 2 2 2
## 4 6.0 4.8 5.0 5.0 5.0 5.0 5.0 5.0 5.0 5.0 5.0 5.0 5.0 2 1 2
## 5 4.5 4.5 4.0 4.6 4.6 5.6 6.0 3.3 3.0 5.5 5.0 5.0 4.2 2 1 2
## 6 4.0 3.9 4.7 4.4 3.0 5.4 5.3 2.7 3.0 2.0 2.5 2.0 5.0 2 1 2
## WC_Bus Gender MarriedStatus Occupation Education Income
## 1 1 2 1 1 2 1
## 2 2 2 1 1 2 1
## 3 2 1 1 1 2 1
## 4 1 1 1 1 2 1
## 5 1 1 1 1 2 1
## 6 1 2 1 1 3 1str(DataLOY)## 'data.frame': 873 obs. of 33 variables:
## $ ID : int 3 4 5 6 7 8 10 11 12 13 ...
## $ AGE : int 1 1 1 1 1 1 4 1 1 2 ...
## $ CITY : int 2 2 2 2 2 2 2 2 2 2 ...
## $ FRE : int 1 2 1 1 1 1 1 1 1 1 ...
## $ TripPurpose : int 5 7 5 5 5 5 4 5 5 5 ...
## $ Departure : int 0 0 1 1 1 1 1 1 0 1 ...
## $ TimeUseonBus : int 4 4 4 1 4 6 4 4 3 3 ...
## $ TravelTime : num 3 2 0.17 4 2 2 2 2.5 1.5 2 ...
## $ PSSW : num 4.9 3.4 3.9 4.1 3.7 4.6 3.9 3.4 5.3 4 ...
## $ PSSS : num 5.4 2.4 3.4 4.4 2.6 2.7 4 2.7 3.1 4.7 ...
## $ PSAB : num 5.5 3.5 4.5 5.5 3.5 3.8 6 3.5 4.8 5.5 ...
## $ PSEB : num 5.8 6 4.5 6 4.5 4 4.5 6.3 7 4.5 ...
## $ PSQ : num 4.8 4.6 2.7 4.8 4.5 3.9 4.2 4.1 6 4.5 ...
## $ SAT : num 6 4.7 2 5 4 4.7 6.7 5 7 6.3 ...
## $ LOY : num 5.7 4.3 3.7 5 4.6 4.4 6.6 5.3 5.9 5.6 ...
## $ IMA : num 5.6 4.8 3 5 4.6 3 5.8 5.8 6.8 6 ...
## $ PHB : num 6.6 4 5 5 5.6 5.4 5.8 5.6 7 6.4 ...
## $ PEV : num 4 5.3 5.8 5 6 5.3 6.3 6.5 7 5.3 ...
## $ ATM : num 4.3 4.1 3.1 5 3.3 2.7 4 4.1 4.4 3.9 ...
## $ PPI : num 6 4 2.7 5 3 3 6 2 3.3 5.3 ...
## $ SIM : num 3.5 4 3.5 5 5.5 2 6 5.3 4.3 6 ...
## $ PPA : num 4.5 4 4.5 5 5 2.5 4 4 4 4.3 ...
## $ SBE : num 4 4.8 6 5 5 2 5.3 4 5 3.8 ...
## $ EXB : num 4.8 4.2 4 5 4.2 5 5.3 5.3 5.3 5 ...
## $ EC_Stop : int 2 2 2 2 2 2 2 2 2 2 ...
## $ WC_Stop : int 1 2 2 1 1 1 2 1 2 2 ...
## $ EC_Bus : int 2 1 2 2 2 2 2 2 2 2 ...
## $ WC_Bus : int 1 2 2 1 1 1 2 1 2 2 ...
## $ Gender : int 2 2 1 1 1 2 2 2 2 1 ...
## $ MarriedStatus: int 1 1 1 1 1 1 2 1 1 1 ...
## $ Occupation : int 1 1 1 1 1 1 2 1 1 7 ...
## $ Education : int 2 2 2 2 2 3 1 2 3 5 ...
## $ Income : int 1 1 1 1 1 1 1 1 1 1 ...attach(DataLOY)
DataLOY = within(DataLOY, {
AGE = factor(AGE, labels = c("16-25", "26-35", "36-45", "46-55", ">55"))
CITY = factor(CITY,labels = c("DaNang", "HoChiMinh"))
FRE = factor(FRE, labels = c(">=3 days/week", "2days/month-2days/week", "2days/year-1day/month", "<2 days/year"))
TripPurpose = factor(TripPurpose, labels = c("Working", "Studying", "Shopping", "Entertaining", "Others"))
Departure = factor(Departure, labels = c("Normal", "Peak-Hour"))
TimeUseonBus = factor(TimeUseonBus, labels = c("Using.telephone", "Reading", "Listening", "Nothing", "Talking", "Others"))
EC_Stop = factor(EC_Stop, labels = c("Ever", "Never"))
WC_Stop = factor(WC_Stop, labels = c("Ever", "Never"))
EC_Bus = factor(EC_Bus, labels = c("Ever", "Never"))
WC_Bus = factor(WC_Bus, labels = c("Ever", "Never"))
Gender = factor(Gender, labels = c("Male", "Female"))
MarriedStatus = factor(MarriedStatus, labels = c("Single", "Married"))
Occupation = factor(Occupation, labels = c("Students/Pupils", "Full.time.job", "Part.time.job", "Retirement", "No.job", "Housewife", "Others"))
Education = factor(Education, labels = c("Secondary.school", "Undergraduate", "High.school", "Postgraduate", "Others"))
Income = factor(Income, labels = c("<5millions", "5-10millions", "10-15millions", ">15millions"))
} )
str(DataLOY)## 'data.frame': 873 obs. of 33 variables:
## $ ID : int 3 4 5 6 7 8 10 11 12 13 ...
## $ AGE : Factor w/ 5 levels "16-25","26-35",..: 1 1 1 1 1 1 3 1 1 2 ...
## $ CITY : Factor w/ 2 levels "DaNang","HoChiMinh": 2 2 2 2 2 2 2 2 2 2 ...
## $ FRE : Factor w/ 4 levels ">=3 days/week",..: 1 2 1 1 1 1 1 1 1 1 ...
## $ TripPurpose : Factor w/ 5 levels "Working","Studying",..: 2 4 2 2 2 2 1 2 2 2 ...
## $ Departure : Factor w/ 2 levels "Normal","Peak-Hour": 1 1 2 2 2 2 2 2 1 2 ...
## $ TimeUseonBus : Factor w/ 6 levels "Using.telephone",..: 4 4 4 1 4 6 4 4 3 3 ...
## $ TravelTime : num 3 2 0.17 4 2 2 2 2.5 1.5 2 ...
## $ PSSW : num 4.9 3.4 3.9 4.1 3.7 4.6 3.9 3.4 5.3 4 ...
## $ PSSS : num 5.4 2.4 3.4 4.4 2.6 2.7 4 2.7 3.1 4.7 ...
## $ PSAB : num 5.5 3.5 4.5 5.5 3.5 3.8 6 3.5 4.8 5.5 ...
## $ PSEB : num 5.8 6 4.5 6 4.5 4 4.5 6.3 7 4.5 ...
## $ PSQ : num 4.8 4.6 2.7 4.8 4.5 3.9 4.2 4.1 6 4.5 ...
## $ SAT : num 6 4.7 2 5 4 4.7 6.7 5 7 6.3 ...
## $ LOY : num 5.7 4.3 3.7 5 4.6 4.4 6.6 5.3 5.9 5.6 ...
## $ IMA : num 5.6 4.8 3 5 4.6 3 5.8 5.8 6.8 6 ...
## $ PHB : num 6.6 4 5 5 5.6 5.4 5.8 5.6 7 6.4 ...
## $ PEV : num 4 5.3 5.8 5 6 5.3 6.3 6.5 7 5.3 ...
## $ ATM : num 4.3 4.1 3.1 5 3.3 2.7 4 4.1 4.4 3.9 ...
## $ PPI : num 6 4 2.7 5 3 3 6 2 3.3 5.3 ...
## $ SIM : num 3.5 4 3.5 5 5.5 2 6 5.3 4.3 6 ...
## $ PPA : num 4.5 4 4.5 5 5 2.5 4 4 4 4.3 ...
## $ SBE : num 4 4.8 6 5 5 2 5.3 4 5 3.8 ...
## $ EXB : num 4.8 4.2 4 5 4.2 5 5.3 5.3 5.3 5 ...
## $ EC_Stop : Factor w/ 2 levels "Ever","Never": 2 2 2 2 2 2 2 2 2 2 ...
## $ WC_Stop : Factor w/ 2 levels "Ever","Never": 1 2 2 1 1 1 2 1 2 2 ...
## $ EC_Bus : Factor w/ 2 levels "Ever","Never": 2 1 2 2 2 2 2 2 2 2 ...
## $ WC_Bus : Factor w/ 2 levels "Ever","Never": 1 2 2 1 1 1 2 1 2 2 ...
## $ Gender : Factor w/ 2 levels "Male","Female": 2 2 1 1 1 2 2 2 2 1 ...
## $ MarriedStatus: Factor w/ 2 levels "Single","Married": 1 1 1 1 1 1 2 1 1 1 ...
## $ Occupation : Factor w/ 7 levels "Students/Pupils",..: 1 1 1 1 1 1 2 1 1 7 ...
## $ Education : Factor w/ 5 levels "Secondary.school",..: 2 2 2 2 2 3 1 2 3 5 ...
## $ Income : Factor w/ 4 levels "<5millions","5-10millions",..: 1 1 1 1 1 1 1 1 1 1 ...dim(DataLOY)## [1] 873 33# 2.3. Descritive Table
library(tableone)
require(tableone)
library(magrittr)
summary(DataLOY)## ID AGE CITY FRE
## Min. : 3.0 16-25:425 DaNang :422 >=3 days/week :508
## 1st Qu.:273.0 26-35:172 HoChiMinh:451 2days/month-2days/week:168
## Median :526.0 36-45:105 2days/year-1day/month : 99
## Mean :521.7 46-55: 77 <2 days/year : 98
## 3rd Qu.:769.0 >55 : 94
## Max. :993.0
##
## TripPurpose Departure TimeUseonBus TravelTime
## Working :305 Normal :296 Using.telephone:198 Min. : 0.000
## Studying :303 Peak-Hour:577 Reading : 53 1st Qu.: 0.500
## Shopping : 60 Listening :138 Median : 1.000
## Entertaining:100 Nothing :428 Mean : 1.291
## Others :105 Talking : 34 3rd Qu.: 2.000
## Others : 22 Max. :20.000
##
## PSSW PSSS PSAB PSEB
## Min. :1.000 Min. :1.000 Min. :1.000 Min. :1.000
## 1st Qu.:4.300 1st Qu.:3.700 1st Qu.:4.000 1st Qu.:5.500
## Median :4.900 Median :4.600 Median :5.500 Median :6.000
## Mean :4.768 Mean :4.478 Mean :5.047 Mean :5.786
## 3rd Qu.:5.400 3rd Qu.:5.400 3rd Qu.:6.000 3rd Qu.:6.300
## Max. :7.000 Max. :7.000 Max. :7.000 Max. :7.000
##
## PSQ SAT LOY IMA
## Min. :1.000 Min. :1.000 Min. :1.000 Min. :1.000
## 1st Qu.:4.800 1st Qu.:5.000 1st Qu.:4.900 1st Qu.:4.800
## Median :5.400 Median :5.700 Median :5.700 Median :5.600
## Mean :5.226 Mean :5.464 Mean :5.436 Mean :5.338
## 3rd Qu.:5.800 3rd Qu.:6.000 3rd Qu.:6.000 3rd Qu.:6.000
## Max. :7.000 Max. :7.000 Max. :7.000 Max. :7.000
##
## PHB PEV ATM PPI
## Min. :1.000 Min. :1.000 Min. :1.000 Min. :1.000
## 1st Qu.:5.200 1st Qu.:5.300 1st Qu.:4.300 1st Qu.:3.700
## Median :5.800 Median :6.000 Median :5.100 Median :4.300
## Mean :5.611 Mean :5.619 Mean :4.979 Mean :4.373
## 3rd Qu.:6.200 3rd Qu.:6.300 3rd Qu.:5.900 3rd Qu.:5.300
## Max. :7.000 Max. :7.000 Max. :7.000 Max. :7.000
##
## SIM PPA SBE EXB EC_Stop
## Min. :1.000 Min. :1.000 Min. :1.80 Min. :2.00 Ever : 36
## 1st Qu.:4.000 1st Qu.:4.000 1st Qu.:4.30 1st Qu.:5.00 Never:837
## Median :5.000 Median :5.000 Median :5.30 Median :5.80
## Mean :4.901 Mean :4.957 Mean :5.18 Mean :5.59
## 3rd Qu.:6.000 3rd Qu.:5.800 3rd Qu.:6.00 3rd Qu.:6.00
## Max. :7.000 Max. :7.000 Max. :7.00 Max. :7.00
##
## WC_Stop EC_Bus WC_Bus Gender MarriedStatus
## Ever :121 Ever : 42 Ever :116 Male :364 Single :535
## Never:752 Never:831 Never:757 Female:509 Married:338
##
##
##
##
##
## Occupation Education Income
## Students/Pupils:368 Secondary.school: 57 <5millions :465
## Full.time.job :305 Undergraduate :287 5-10millions :249
## Part.time.job : 69 High.school :368 10-15millions:122
## Retirement : 46 Postgraduate :106 >15millions : 37
## No.job : 3 Others : 55
## Housewife : 54
## Others : 28library(table1)##
## Attaching package: 'table1'## The following objects are masked from 'package:base':
##
## units, units<-Tab1_LOY <- table1(~ PSSW + PSSS + PSAB + PSEB + PSQ + SAT + LOY + IMA + PHB + PEV + ATM + PPI + SIM + PPA + SBE + EXB + EC_Stop + WC_Stop + EC_Bus + WC_Bus + Gender + MarriedStatus + Occupation + Education + Income + AGE + FRE + TripPurpose + Departure + TimeUseonBus + TravelTime| CITY , data = DataLOY)
Tab1_LOY| DaNang (N=422) |
HoChiMinh (N=451) |
Overall (N=873) |
|
|---|---|---|---|
| PSSW | |||
| Mean (SD) | 5.13 (0.814) | 4.43 (1.05) | 4.77 (1.01) |
| Median [Min, Max] | 5.30 [1.00, 7.00] | 4.60 [1.00, 7.00] | 4.90 [1.00, 7.00] |
| PSSS | |||
| Mean (SD) | 4.83 (1.01) | 4.15 (1.22) | 4.48 (1.17) |
| Median [Min, Max] | 4.90 [1.00, 7.00] | 4.30 [1.00, 7.00] | 4.60 [1.00, 7.00] |
| PSAB | |||
| Mean (SD) | 5.57 (1.03) | 4.56 (1.27) | 5.05 (1.26) |
| Median [Min, Max] | 5.80 [1.50, 7.00] | 4.80 [1.00, 7.00] | 5.50 [1.00, 7.00] |
| PSEB | |||
| Mean (SD) | 5.98 (0.885) | 5.61 (0.969) | 5.79 (0.948) |
| Median [Min, Max] | 6.00 [1.00, 7.00] | 6.00 [1.00, 7.00] | 6.00 [1.00, 7.00] |
| PSQ | |||
| Mean (SD) | 5.44 (0.713) | 5.02 (0.953) | 5.23 (0.871) |
| Median [Min, Max] | 5.60 [1.50, 7.00] | 5.10 [1.00, 7.00] | 5.40 [1.00, 7.00] |
| SAT | |||
| Mean (SD) | 5.63 (0.909) | 5.31 (1.14) | 5.46 (1.05) |
| Median [Min, Max] | 6.00 [2.00, 7.00] | 5.70 [1.00, 7.00] | 5.70 [1.00, 7.00] |
| LOY | |||
| Mean (SD) | 5.64 (0.835) | 5.25 (1.07) | 5.44 (0.984) |
| Median [Min, Max] | 5.70 [2.00, 7.00] | 5.60 [1.00, 7.00] | 5.70 [1.00, 7.00] |
| IMA | |||
| Mean (SD) | 5.55 (0.754) | 5.14 (1.09) | 5.34 (0.964) |
| Median [Min, Max] | 5.60 [2.80, 7.00] | 5.40 [1.00, 7.00] | 5.60 [1.00, 7.00] |
| PHB | |||
| Mean (SD) | 5.72 (0.789) | 5.51 (1.16) | 5.61 (1.00) |
| Median [Min, Max] | 5.80 [2.60, 7.00] | 6.00 [1.00, 7.00] | 5.80 [1.00, 7.00] |
| PEV | |||
| Mean (SD) | 5.77 (0.877) | 5.48 (1.44) | 5.62 (1.21) |
| Median [Min, Max] | 6.00 [1.00, 7.00] | 6.00 [1.00, 7.00] | 6.00 [1.00, 7.00] |
| ATM | |||
| Mean (SD) | 5.35 (0.944) | 4.63 (1.24) | 4.98 (1.16) |
| Median [Min, Max] | 5.60 [1.90, 7.00] | 4.70 [1.00, 7.00] | 5.10 [1.00, 7.00] |
| PPI | |||
| Mean (SD) | 4.76 (1.23) | 4.01 (1.48) | 4.37 (1.41) |
| Median [Min, Max] | 5.00 [1.00, 7.00] | 4.00 [1.00, 7.00] | 4.30 [1.00, 7.00] |
| SIM | |||
| Mean (SD) | 5.13 (1.09) | 4.69 (1.15) | 4.90 (1.14) |
| Median [Min, Max] | 5.50 [1.00, 7.00] | 4.50 [1.00, 7.00] | 5.00 [1.00, 7.00] |
| PPA | |||
| Mean (SD) | 5.23 (0.924) | 4.70 (1.04) | 4.96 (1.02) |
| Median [Min, Max] | 5.50 [2.00, 7.00] | 4.50 [1.00, 7.00] | 5.00 [1.00, 7.00] |
| SBE | |||
| Mean (SD) | 5.57 (0.846) | 4.82 (1.09) | 5.18 (1.05) |
| Median [Min, Max] | 5.80 [1.80, 7.00] | 5.00 [1.80, 7.00] | 5.30 [1.80, 7.00] |
| EXB | |||
| Mean (SD) | 5.72 (0.751) | 5.47 (0.973) | 5.59 (0.881) |
| Median [Min, Max] | 5.80 [2.50, 7.00] | 5.70 [2.00, 7.00] | 5.80 [2.00, 7.00] |
| EC_Stop | |||
| Ever | 4 (0.9%) | 32 (7.1%) | 36 (4.1%) |
| Never | 418 (99.1%) | 419 (92.9%) | 837 (95.9%) |
| WC_Stop | |||
| Ever | 22 (5.2%) | 99 (22.0%) | 121 (13.9%) |
| Never | 400 (94.8%) | 352 (78.0%) | 752 (86.1%) |
| EC_Bus | |||
| Ever | 3 (0.7%) | 39 (8.6%) | 42 (4.8%) |
| Never | 419 (99.3%) | 412 (91.4%) | 831 (95.2%) |
| WC_Bus | |||
| Ever | 17 (4.0%) | 99 (22.0%) | 116 (13.3%) |
| Never | 405 (96.0%) | 352 (78.0%) | 757 (86.7%) |
| Gender | |||
| Male | 188 (44.5%) | 176 (39.0%) | 364 (41.7%) |
| Female | 234 (55.5%) | 275 (61.0%) | 509 (58.3%) |
| MarriedStatus | |||
| Single | 270 (64.0%) | 265 (58.8%) | 535 (61.3%) |
| Married | 152 (36.0%) | 186 (41.2%) | 338 (38.7%) |
| Occupation | |||
| Students/Pupils | 207 (49.1%) | 161 (35.7%) | 368 (42.2%) |
| Full.time.job | 116 (27.5%) | 189 (41.9%) | 305 (34.9%) |
| Part.time.job | 28 (6.6%) | 41 (9.1%) | 69 (7.9%) |
| Retirement | 33 (7.8%) | 13 (2.9%) | 46 (5.3%) |
| No.job | 3 (0.7%) | 0 (0%) | 3 (0.3%) |
| Housewife | 27 (6.4%) | 27 (6.0%) | 54 (6.2%) |
| Others | 8 (1.9%) | 20 (4.4%) | 28 (3.2%) |
| Education | |||
| Secondary.school | 30 (7.1%) | 27 (6.0%) | 57 (6.5%) |
| Undergraduate | 134 (31.8%) | 153 (33.9%) | 287 (32.9%) |
| High.school | 176 (41.7%) | 192 (42.6%) | 368 (42.2%) |
| Postgraduate | 63 (14.9%) | 43 (9.5%) | 106 (12.1%) |
| Others | 19 (4.5%) | 36 (8.0%) | 55 (6.3%) |
| Income | |||
| <5millions | 276 (65.4%) | 189 (41.9%) | 465 (53.3%) |
| 5-10millions | 86 (20.4%) | 163 (36.1%) | 249 (28.5%) |
| 10-15millions | 51 (12.1%) | 71 (15.7%) | 122 (14.0%) |
| >15millions | 9 (2.1%) | 28 (6.2%) | 37 (4.2%) |
| AGE | |||
| 16-25 | 226 (53.6%) | 199 (44.1%) | 425 (48.7%) |
| 26-35 | 76 (18.0%) | 96 (21.3%) | 172 (19.7%) |
| 36-45 | 37 (8.8%) | 68 (15.1%) | 105 (12.0%) |
| 46-55 | 36 (8.5%) | 41 (9.1%) | 77 (8.8%) |
| >55 | 47 (11.1%) | 47 (10.4%) | 94 (10.8%) |
| FRE | |||
| >=3 days/week | 269 (63.7%) | 239 (53.0%) | 508 (58.2%) |
| 2days/month-2days/week | 85 (20.1%) | 83 (18.4%) | 168 (19.2%) |
| 2days/year-1day/month | 29 (6.9%) | 70 (15.5%) | 99 (11.3%) |
| <2 days/year | 39 (9.2%) | 59 (13.1%) | 98 (11.2%) |
| TripPurpose | |||
| Working | 117 (27.7%) | 188 (41.7%) | 305 (34.9%) |
| Studying | 168 (39.8%) | 135 (29.9%) | 303 (34.7%) |
| Shopping | 46 (10.9%) | 14 (3.1%) | 60 (6.9%) |
| Entertaining | 53 (12.6%) | 47 (10.4%) | 100 (11.5%) |
| Others | 38 (9.0%) | 67 (14.9%) | 105 (12.0%) |
| Departure | |||
| Normal | 151 (35.8%) | 145 (32.2%) | 296 (33.9%) |
| Peak-Hour | 271 (64.2%) | 306 (67.8%) | 577 (66.1%) |
| TimeUseonBus | |||
| Using.telephone | 107 (25.4%) | 91 (20.2%) | 198 (22.7%) |
| Reading | 22 (5.2%) | 31 (6.9%) | 53 (6.1%) |
| Listening | 55 (13.0%) | 83 (18.4%) | 138 (15.8%) |
| Nothing | 207 (49.1%) | 221 (49.0%) | 428 (49.0%) |
| Talking | 25 (5.9%) | 9 (2.0%) | 34 (3.9%) |
| Others | 6 (1.4%) | 16 (3.5%) | 22 (2.5%) |
| TravelTime | |||
| Mean (SD) | 1.12 (0.826) | 1.45 (1.86) | 1.29 (1.46) |
| Median [Min, Max] | 1.00 [0, 6.00] | 1.00 [0, 20.0] | 1.00 [0, 20.0] |
library(compareGroups)
Des_LOY <- compareGroups(CITY ~ PSSW + PSSS + PSAB + PSEB + PSQ + SAT + LOY + IMA + PHB + PEV + ATM + PPI + SIM + PPA + SBE + EXB + EC_Stop + WC_Stop + EC_Bus + WC_Bus + Gender + MarriedStatus + Occupation + Education + Income + AGE + FRE + TripPurpose + Departure + TimeUseonBus + TravelTime, data = DataLOY)
createTable(Des_LOY)##
## --------Summary descriptives table by 'CITY'---------
##
## ____________________________________________________________
## DaNang HoChiMinh p.overall
## N=422 N=451
## ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
## PSSW 5.13 (0.81) 4.43 (1.05) <0.001
## PSSS 4.83 (1.01) 4.15 (1.22) <0.001
## PSAB 5.57 (1.03) 4.56 (1.27) <0.001
## PSEB 5.98 (0.89) 5.61 (0.97) <0.001
## PSQ 5.44 (0.71) 5.02 (0.95) <0.001
## SAT 5.63 (0.91) 5.31 (1.14) <0.001
## LOY 5.64 (0.83) 5.25 (1.07) <0.001
## IMA 5.55 (0.75) 5.14 (1.09) <0.001
## PHB 5.72 (0.79) 5.51 (1.16) 0.001
## PEV 5.77 (0.88) 5.48 (1.44) <0.001
## ATM 5.35 (0.94) 4.63 (1.24) <0.001
## PPI 4.76 (1.23) 4.01 (1.48) <0.001
## SIM 5.13 (1.09) 4.69 (1.15) <0.001
## PPA 5.23 (0.92) 4.70 (1.04) <0.001
## SBE 5.57 (0.85) 4.82 (1.09) <0.001
## EXB 5.72 (0.75) 5.47 (0.97) <0.001
## EC_Stop: <0.001
## Ever 4 (0.95%) 32 (7.10%)
## Never 418 (99.1%) 419 (92.9%)
## WC_Stop: <0.001
## Ever 22 (5.21%) 99 (22.0%)
## Never 400 (94.8%) 352 (78.0%)
## EC_Bus: <0.001
## Ever 3 (0.71%) 39 (8.65%)
## Never 419 (99.3%) 412 (91.4%)
## WC_Bus: <0.001
## Ever 17 (4.03%) 99 (22.0%)
## Never 405 (96.0%) 352 (78.0%)
## Gender: 0.113
## Male 188 (44.5%) 176 (39.0%)
## Female 234 (55.5%) 275 (61.0%)
## MarriedStatus: 0.130
## Single 270 (64.0%) 265 (58.8%)
## Married 152 (36.0%) 186 (41.2%)
## Occupation: .
## Students/Pupils 207 (49.1%) 161 (35.7%)
## Full.time.job 116 (27.5%) 189 (41.9%)
## Part.time.job 28 (6.64%) 41 (9.09%)
## Retirement 33 (7.82%) 13 (2.88%)
## No.job 3 (0.71%) 0 (0.00%)
## Housewife 27 (6.40%) 27 (5.99%)
## Others 8 (1.90%) 20 (4.43%)
## Education: 0.037
## Secondary.school 30 (7.11%) 27 (5.99%)
## Undergraduate 134 (31.8%) 153 (33.9%)
## High.school 176 (41.7%) 192 (42.6%)
## Postgraduate 63 (14.9%) 43 (9.53%)
## Others 19 (4.50%) 36 (7.98%)
## Income: <0.001
## <5millions 276 (65.4%) 189 (41.9%)
## 5-10millions 86 (20.4%) 163 (36.1%)
## 10-15millions 51 (12.1%) 71 (15.7%)
## >15millions 9 (2.13%) 28 (6.21%)
## AGE: 0.014
## 16-25 226 (53.6%) 199 (44.1%)
## 26-35 76 (18.0%) 96 (21.3%)
## 36-45 37 (8.77%) 68 (15.1%)
## 46-55 36 (8.53%) 41 (9.09%)
## >55 47 (11.1%) 47 (10.4%)
## FRE: <0.001
## >=3 days/week 269 (63.7%) 239 (53.0%)
## 2days/month-2days/week 85 (20.1%) 83 (18.4%)
## 2days/year-1day/month 29 (6.87%) 70 (15.5%)
## <2 days/year 39 (9.24%) 59 (13.1%)
## TripPurpose: <0.001
## Working 117 (27.7%) 188 (41.7%)
## Studying 168 (39.8%) 135 (29.9%)
## Shopping 46 (10.9%) 14 (3.10%)
## Entertaining 53 (12.6%) 47 (10.4%)
## Others 38 (9.00%) 67 (14.9%)
## Departure: 0.289
## Normal 151 (35.8%) 145 (32.2%)
## Peak-Hour 271 (64.2%) 306 (67.8%)
## TimeUseonBus: 0.001
## Using.telephone 107 (25.4%) 91 (20.2%)
## Reading 22 (5.21%) 31 (6.87%)
## Listening 55 (13.0%) 83 (18.4%)
## Nothing 207 (49.1%) 221 (49.0%)
## Talking 25 (5.92%) 9 (2.00%)
## Others 6 (1.42%) 16 (3.55%)
## TravelTime 1.12 (0.83) 1.45 (1.86) 0.001
## ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯3. Describe Data by graph
library(magrittr)
library(tidyverse)## -- Attaching packages --------------------------------------- tidyverse 1.3.0 --## v ggplot2 3.3.2 v purrr 0.3.4
## v tibble 3.0.4 v dplyr 1.0.2
## v tidyr 1.1.2 v stringr 1.4.0
## v readr 1.4.0 v forcats 0.5.0## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x tidyr::extract() masks magrittr::extract()
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()
## x purrr::set_names() masks magrittr::set_names()library(ggplot2)
library(car)## Warning: package 'car' was built under R version 4.0.4## Loading required package: carData##
## Attaching package: 'car'## The following object is masked from 'package:dplyr':
##
## recode## The following object is masked from 'package:purrr':
##
## somelibrary(psych)##
## Attaching package: 'psych'## The following object is masked from 'package:car':
##
## logit## The following objects are masked from 'package:ggplot2':
##
## %+%, alphalibrary(gridExtra)##
## Attaching package: 'gridExtra'## The following object is masked from 'package:dplyr':
##
## combinehist(DataLOY$LOY)
# Correlations between LOY and continuous variables of users' perception
Cor1_1 = data.frame(DataLOY$LOY, DataLOY$PSSW, DataLOY$PSSS, DataLOY$PSAB, DataLOY$PSEB, DataLOY$PSQ, DataLOY$SAT, DataLOY$IMA)
pairs.panels(Cor1_1)
Cor1_2 = data.frame(DataLOY$LOY, DataLOY$PHB, DataLOY$PEV, DataLOY$ATM, DataLOY$PPI, DataLOY$SIM, DataLOY$PPA, DataLOY$SBE, DataLOY$EXB)
pairs.panels(Cor1_2)
# Correlation between LOY and variables of users experiences
Cor2 = data.frame(DataLOY$LOY, DataLOY$EC_Stop, DataLOY$WC_Stop, DataLOY$EC_Bus, DataLOY$WC_Bus)
pairs.panels(Cor2)
# Correlation between LOY and variables of travel characteristics
Cor3 = data.frame(DataLOY$LOY, DataLOY$CITY, DataLOY$FRE, DataLOY$TripPurpose, DataLOY$Departure, DataLOY$TimeUseonBus, DataLOY$TravelTime)
pairs.panels(Cor3)
# Correlation between LOY and variables of socioeconomics
Cor4 = data.frame(DataLOY$LOY, DataLOY$Gender, DataLOY$MarriedStatus, DataLOY$Occupation, DataLOY$Education, DataLOY$Income, DataLOY$AGE)
pairs.panels(Cor4)
# Boxplot of variables/CITY
# Chia cot theo cach khac : library(gridExtra) ; grid.arrange(p1, p2, ncol=2)
par(mfrow = c(1,2))
boxplot (DataLOY$PSSW ~ DataLOY$CITY, main = "Perceived Security & Safety on the way to/from bus stops", xlab = "PSSW", ylab = "Point (1-7)", col = c("Red", "blue"), notch = T, names = c("Da Nang", "Ho Chi Minh"))
boxplot (DataLOY$PSSW ~ DataLOY$Gender, main = "Perceived Security & Safety on the way to/from bus stops", xlab = "PSSW", ylab = "Point (1-7)", col = c("Red", "blue"), notch = T, names = c("Male", "Female"))
boxplot (DataLOY$PSSS ~ DataLOY$CITY, main = "Perceived Security & Safety at bus Stations", xlab = "PSSS", ylab = "Point (1-7)", col = c("Red", "blue"), notch = T, names = c("Da Nang", "Ho Chi Minh"))
boxplot (DataLOY$PSSS ~ DataLOY$Gender, main = "Perceived Security & Safety at bus Stations", xlab = "PSSS", ylab = "Point (1-7)", col = c("Red", "blue"), notch = T, names = c("Male", "Female"))
boxplot (DataLOY$PSAB ~ DataLOY$CITY, main = "Perceived Safety on Buses", xlab = "PSAB", ylab = "Point (1-7)", col = c("Red", "blue"), notch = T, names = c("Da Nang", "Ho Chi Minh"))
boxplot (DataLOY$PSAB ~ DataLOY$Gender, main = "Perceived Safety on Buses", xlab = "PSAB", ylab = "Point (1-7)", col = c("Red", "blue"), notch = T, names = c("Male", "Female"))
boxplot (DataLOY$PSEB ~ DataLOY$CITY, main = "Perceived Security on Buses", xlab = "PSEB", ylab = "Point (1-7)", col = c("Red", "blue"), notch = T, names = c("Da Nang", "Ho Chi Minh"))## Warning in bxp(list(stats = structure(c(4.8, 5.8, 6, 6.5, 7, 3.5, 5, 6, : some
## notches went outside hinges ('box'): maybe set notch=FALSEboxplot (DataLOY$PSEB ~ DataLOY$Gender, main = "Perceived Security on Buses", xlab = "PSEB", ylab = "Point (1-7)", col = c("Red", "blue"), notch = T, names = c("Male", "Female"))
boxplot (DataLOY$PSQ ~ DataLOY$CITY, main = "Perceived Service Quality", xlab = "PSQ", ylab = "Point (1-7)", col = c("Red", "blue"), notch = T, names = c("Da Nang", "Ho Chi Minh"))
boxplot (DataLOY$PSQ ~ DataLOY$Gender, main = "Perceived Service Quality", xlab = "PSQ", ylab = "Point (1-7)", col = c("Red", "blue"), notch = T, names = c("Male", "Female"))
boxplot (DataLOY$IMA ~ DataLOY$CITY, main = "Perceived Image", xlab = "IMA", ylab = "Point (1-7)", col = c("Red", "blue"), notch = T, names = c("Da Nang", "Ho Chi Minh"))
boxplot (DataLOY$IMA ~ DataLOY$Gender, main = "Perceived Image", xlab = "IMA", ylab = "Point (1-7)", col = c("Red", "blue"), notch = T, names = c("Male", "Female"))
boxplot (DataLOY$PHB ~ DataLOY$CITY, main = "Perceived Health Benefits", xlab = "PHB", ylab = "Point (1-7)", col = c("Red", "blue"), notch = T, names = c("Da Nang", "Ho Chi Minh"))## Warning in bxp(list(stats = structure(c(4.4, 5.4, 5.8, 6.2, 7, 3.6, 5, 6, : some
## notches went outside hinges ('box'): maybe set notch=FALSEboxplot (DataLOY$PHB ~ DataLOY$Gender, main = "Perceived Health Benefits", xlab = "PHB", ylab = "Point (1-7)", col = c("Red", "blue"), notch = T, names = c("Male", "Female"))
boxplot (DataLOY$PEV ~ DataLOY$CITY, main = "Perceived Environment Value/Benefits", xlab = "PEV", ylab = "Point (1-7)", col = c("Red", "blue"), notch = T, names = c("Da Nang", "Ho Chi Minh"))
boxplot (DataLOY$PEV ~ DataLOY$Gender, main = "Perceived Environment Value/Benefits", xlab = "PEV", ylab = "Point (1-7)", col = c("Red", "blue"), notch = T, names = c("Male", "Female"))
boxplot (DataLOY$ATM ~ DataLOY$CITY, main = "Perceived Atmospheric", xlab = "ATM", ylab = "Point (1-7)", col = c("Red", "blue"), notch = T, names = c("Da Nang", "Ho Chi Minh"))
boxplot (DataLOY$ATM ~ DataLOY$Gender, main = "Perceived Atmospheric", xlab = "ATM", ylab = "Point (1-7)", col = c("Red", "blue"), notch = T, names = c("Male", "Female"))
boxplot (DataLOY$PPI ~ DataLOY$CITY, main = "Passenger to Passenger Interaction", xlab = "PPI", ylab = "Point (1-7)", col = c("Red", "blue"), notch = T, names = c("Da Nang", "Ho Chi Minh"))
boxplot (DataLOY$PPI ~ DataLOY$Gender, main = "Passenger to Passenger Interaction", xlab = "PPI", ylab = "Point (1-7)", col = c("Red", "blue"), notch = T, names = c("Male", "Female"))
boxplot (DataLOY$SIM ~ DataLOY$CITY, main = "Similarity", xlab = "SIM", ylab = "Point (1-7)", col = c("Red", "blue"), notch = T, names = c("Da Nang", "Ho Chi Minh"))
boxplot (DataLOY$SIM ~ DataLOY$Gender, main = "Similarity", xlab = "SIM", ylab = "Point (1-7)", col = c("Red", "blue"), notch = T, names = c("Male", "Female"))
boxplot (DataLOY$PPA ~ DataLOY$CITY, main = "Perceived Physical Appearance", xlab = "PPA", ylab = "Point (1-7)", col = c("Red", "blue"), notch = T, names = c("Da Nang", "Ho Chi Minh"))
boxplot (DataLOY$PPA ~ DataLOY$Gender, main = "Perceived Physical Appearance", xlab = "PPA", ylab = "Point (1-7)", col = c("Red", "blue"), notch = T, names = c("Male", "Female"))
boxplot (DataLOY$SBE ~ DataLOY$CITY, main = "Perceived Suitable Behavior", xlab = "SBE", ylab = "Point (1-7)", col = c("Red", "blue"), notch = T, names = c("Da Nang", "Ho Chi Minh"))
boxplot (DataLOY$SBE ~ DataLOY$Gender, main = "Perceived Suitable Behavior", xlab = "SBE", ylab = "Point (1-7)", col = c("Red", "blue"), notch = T, names = c("Male", "Female"))
boxplot (DataLOY$EXB ~ DataLOY$CITY, main = "Experience on the Bus", xlab = "EXB", ylab = "Point (1-7)", col = c("Red", "blue"), notch = T, names = c("Da Nang", "Ho Chi Minh"))
boxplot (DataLOY$EXB ~ DataLOY$Gender, main = "Experience on the Bus", xlab = "EXB", ylab = "Point (1-7)", col = c("Red", "blue"), notch = T, names = c("Male", "Female"))
boxplot (DataLOY$LOY ~ DataLOY$CITY, main = "Perceived loyalty", xlab = "LOY", ylab = "Point (1-7)", col = c("Red", "blue"), notch = T, names = c("Da Nang", "Ho Chi Minh"))
boxplot (DataLOY$LOY ~ DataLOY$Gender, main = "Perceived loyalty", xlab = "LOY", ylab = "Point (1-7)", col = c("Red", "blue"), notch = T, names = c("Male", "Female"))
boxplot (DataLOY$SAT ~ DataLOY$CITY, main = "Perceived Satisfaction", xlab = "SAT", ylab = "Point (1-7)", col = c("Red", "blue"), notch = T, names = c("Da Nang", "Ho Chi Minh"))## Warning in bxp(list(stats = structure(c(3.7, 5, 6, 6, 7, 3, 4.7, 5.7, 6, : some
## notches went outside hinges ('box'): maybe set notch=FALSEboxplot (DataLOY$SAT ~ DataLOY$Gender, main = "Perceived Satisfaction", xlab = "SAT", ylab = "Point (1-7)", col = c("Red", "blue"), notch = T, names = c("Male", "Female"))
4. Descriptive statistical analysis
summary(DataLOY)## ID AGE CITY FRE
## Min. : 3.0 16-25:425 DaNang :422 >=3 days/week :508
## 1st Qu.:273.0 26-35:172 HoChiMinh:451 2days/month-2days/week:168
## Median :526.0 36-45:105 2days/year-1day/month : 99
## Mean :521.7 46-55: 77 <2 days/year : 98
## 3rd Qu.:769.0 >55 : 94
## Max. :993.0
##
## TripPurpose Departure TimeUseonBus TravelTime
## Working :305 Normal :296 Using.telephone:198 Min. : 0.000
## Studying :303 Peak-Hour:577 Reading : 53 1st Qu.: 0.500
## Shopping : 60 Listening :138 Median : 1.000
## Entertaining:100 Nothing :428 Mean : 1.291
## Others :105 Talking : 34 3rd Qu.: 2.000
## Others : 22 Max. :20.000
##
## PSSW PSSS PSAB PSEB
## Min. :1.000 Min. :1.000 Min. :1.000 Min. :1.000
## 1st Qu.:4.300 1st Qu.:3.700 1st Qu.:4.000 1st Qu.:5.500
## Median :4.900 Median :4.600 Median :5.500 Median :6.000
## Mean :4.768 Mean :4.478 Mean :5.047 Mean :5.786
## 3rd Qu.:5.400 3rd Qu.:5.400 3rd Qu.:6.000 3rd Qu.:6.300
## Max. :7.000 Max. :7.000 Max. :7.000 Max. :7.000
##
## PSQ SAT LOY IMA
## Min. :1.000 Min. :1.000 Min. :1.000 Min. :1.000
## 1st Qu.:4.800 1st Qu.:5.000 1st Qu.:4.900 1st Qu.:4.800
## Median :5.400 Median :5.700 Median :5.700 Median :5.600
## Mean :5.226 Mean :5.464 Mean :5.436 Mean :5.338
## 3rd Qu.:5.800 3rd Qu.:6.000 3rd Qu.:6.000 3rd Qu.:6.000
## Max. :7.000 Max. :7.000 Max. :7.000 Max. :7.000
##
## PHB PEV ATM PPI
## Min. :1.000 Min. :1.000 Min. :1.000 Min. :1.000
## 1st Qu.:5.200 1st Qu.:5.300 1st Qu.:4.300 1st Qu.:3.700
## Median :5.800 Median :6.000 Median :5.100 Median :4.300
## Mean :5.611 Mean :5.619 Mean :4.979 Mean :4.373
## 3rd Qu.:6.200 3rd Qu.:6.300 3rd Qu.:5.900 3rd Qu.:5.300
## Max. :7.000 Max. :7.000 Max. :7.000 Max. :7.000
##
## SIM PPA SBE EXB EC_Stop
## Min. :1.000 Min. :1.000 Min. :1.80 Min. :2.00 Ever : 36
## 1st Qu.:4.000 1st Qu.:4.000 1st Qu.:4.30 1st Qu.:5.00 Never:837
## Median :5.000 Median :5.000 Median :5.30 Median :5.80
## Mean :4.901 Mean :4.957 Mean :5.18 Mean :5.59
## 3rd Qu.:6.000 3rd Qu.:5.800 3rd Qu.:6.00 3rd Qu.:6.00
## Max. :7.000 Max. :7.000 Max. :7.00 Max. :7.00
##
## WC_Stop EC_Bus WC_Bus Gender MarriedStatus
## Ever :121 Ever : 42 Ever :116 Male :364 Single :535
## Never:752 Never:831 Never:757 Female:509 Married:338
##
##
##
##
##
## Occupation Education Income
## Students/Pupils:368 Secondary.school: 57 <5millions :465
## Full.time.job :305 Undergraduate :287 5-10millions :249
## Part.time.job : 69 High.school :368 10-15millions:122
## Retirement : 46 Postgraduate :106 >15millions : 37
## No.job : 3 Others : 55
## Housewife : 54
## Others : 28table(LOY) ## LOY
## 1 1.9 2 2.1 2.3 2.4 2.6 2.7 2.9 3 3.1 3.3 3.4 3.6 3.7 3.9 4 4.1 4.3 4.4
## 1 1 5 2 1 2 1 3 5 2 8 1 5 3 8 12 29 11 27 23
## 4.6 4.7 4.9 5 5.1 5.3 5.4 5.6 5.7 5.9 6 6.1 6.3 6.4 6.6 6.7 6.9 7
## 26 29 17 45 36 25 26 68 68 40 168 33 32 20 22 17 7 44# Descriptive Statistics of categorical variables
# with(DataLOY, do.call(rbind, tapply(TravelTime, LOY, function(x) c(M = mean(x), SD = sd(x)))))
# with(DataLOY, do.call(rbind, tapply(PSSW, LOY, function(x) c(M = mean(x), SD = sd(x)))))5. Estimate Multinominal Logit Regression Model - DataLOY for 2 cities
library(BMA)## Loading required package: survival## Loading required package: leaps## Loading required package: robustbase##
## Attaching package: 'robustbase'## The following object is masked from 'package:survival':
##
## heart## Loading required package: inline## Loading required package: rrcov## Scalable Robust Estimators with High Breakdown Point (version 1.5-5)attach(DataLOY)## The following objects are masked from DataLOY (pos = 26):
##
## AGE, ATM, CITY, Departure, EC_Bus, EC_Stop, Education, EXB, FRE,
## Gender, ID, IMA, Income, LOY, MarriedStatus, Occupation, PEV, PHB,
## PPA, PPI, PSAB, PSEB, PSQ, PSSS, PSSW, SAT, SBE, SIM, TimeUseonBus,
## TravelTime, TripPurpose, WC_Bus, WC_Stopstr(DataLOY)## 'data.frame': 873 obs. of 33 variables:
## $ ID : int 3 4 5 6 7 8 10 11 12 13 ...
## $ AGE : Factor w/ 5 levels "16-25","26-35",..: 1 1 1 1 1 1 3 1 1 2 ...
## $ CITY : Factor w/ 2 levels "DaNang","HoChiMinh": 2 2 2 2 2 2 2 2 2 2 ...
## $ FRE : Factor w/ 4 levels ">=3 days/week",..: 1 2 1 1 1 1 1 1 1 1 ...
## $ TripPurpose : Factor w/ 5 levels "Working","Studying",..: 2 4 2 2 2 2 1 2 2 2 ...
## $ Departure : Factor w/ 2 levels "Normal","Peak-Hour": 1 1 2 2 2 2 2 2 1 2 ...
## $ TimeUseonBus : Factor w/ 6 levels "Using.telephone",..: 4 4 4 1 4 6 4 4 3 3 ...
## $ TravelTime : num 3 2 0.17 4 2 2 2 2.5 1.5 2 ...
## $ PSSW : num 4.9 3.4 3.9 4.1 3.7 4.6 3.9 3.4 5.3 4 ...
## $ PSSS : num 5.4 2.4 3.4 4.4 2.6 2.7 4 2.7 3.1 4.7 ...
## $ PSAB : num 5.5 3.5 4.5 5.5 3.5 3.8 6 3.5 4.8 5.5 ...
## $ PSEB : num 5.8 6 4.5 6 4.5 4 4.5 6.3 7 4.5 ...
## $ PSQ : num 4.8 4.6 2.7 4.8 4.5 3.9 4.2 4.1 6 4.5 ...
## $ SAT : num 6 4.7 2 5 4 4.7 6.7 5 7 6.3 ...
## $ LOY : num 5.7 4.3 3.7 5 4.6 4.4 6.6 5.3 5.9 5.6 ...
## $ IMA : num 5.6 4.8 3 5 4.6 3 5.8 5.8 6.8 6 ...
## $ PHB : num 6.6 4 5 5 5.6 5.4 5.8 5.6 7 6.4 ...
## $ PEV : num 4 5.3 5.8 5 6 5.3 6.3 6.5 7 5.3 ...
## $ ATM : num 4.3 4.1 3.1 5 3.3 2.7 4 4.1 4.4 3.9 ...
## $ PPI : num 6 4 2.7 5 3 3 6 2 3.3 5.3 ...
## $ SIM : num 3.5 4 3.5 5 5.5 2 6 5.3 4.3 6 ...
## $ PPA : num 4.5 4 4.5 5 5 2.5 4 4 4 4.3 ...
## $ SBE : num 4 4.8 6 5 5 2 5.3 4 5 3.8 ...
## $ EXB : num 4.8 4.2 4 5 4.2 5 5.3 5.3 5.3 5 ...
## $ EC_Stop : Factor w/ 2 levels "Ever","Never": 2 2 2 2 2 2 2 2 2 2 ...
## $ WC_Stop : Factor w/ 2 levels "Ever","Never": 1 2 2 1 1 1 2 1 2 2 ...
## $ EC_Bus : Factor w/ 2 levels "Ever","Never": 2 1 2 2 2 2 2 2 2 2 ...
## $ WC_Bus : Factor w/ 2 levels "Ever","Never": 1 2 2 1 1 1 2 1 2 2 ...
## $ Gender : Factor w/ 2 levels "Male","Female": 2 2 1 1 1 2 2 2 2 1 ...
## $ MarriedStatus: Factor w/ 2 levels "Single","Married": 1 1 1 1 1 1 2 1 1 1 ...
## $ Occupation : Factor w/ 7 levels "Students/Pupils",..: 1 1 1 1 1 1 2 1 1 7 ...
## $ Education : Factor w/ 5 levels "Secondary.school",..: 2 2 2 2 2 3 1 2 3 5 ...
## $ Income : Factor w/ 4 levels "<5millions","5-10millions",..: 1 1 1 1 1 1 1 1 1 1 ...# All variables - rempve: EC_Stop + WC_Stop + EC_Bus + WC_Bus + SAT and variable have cor > 0.7 - AGE, PPA
yvar <- DataLOY$LOY
xvars <- DataLOY[c(3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 16, 17, 18, 19, 20, 21, 23, 24, 29, 30, 31, 32, 33)]
bma <- bicreg(xvars, yvar, strict = F, OR = 20)
summary(bma)##
## Call:
## bicreg(x = xvars, y = yvar, strict = F, OR = 20)
##
##
## 56 models were selected
## Best 5 models (cumulative posterior probability = 0.3461 ):
##
## p!=0 EV SD model 1 model 2
## Intercept 100.0 -0.1075750 0.169367 -0.17388 -0.13105
## CITYHoChiMinh 5.2 -0.0040619 0.020102 . .
## FRE2days.month.2days.week 0.6 -0.0004366 0.006869 . .
## FRE2days.year.1day.month 41.2 -0.0659515 0.088988 . -0.15560
## FRE.2.days.year 100.0 -0.3004670 0.065128 -0.29080 -0.31172
## TripPurposeStudying 0.7 -0.0003732 0.005775 . .
## TripPurposeShopping 26.5 0.0513611 0.095437 . .
## TimeUseonBusReading 0.0 0.0000000 0.000000 . .
## TimeUseonBusTalking 0.0 0.0000000 0.000000 . .
## TravelTime 1.4 -0.0002163 0.002457 . .
## PSAB 8.9 0.0033583 0.012288 . .
## PSEB 0.0 0.0000000 0.000000 . .
## PSQ 100.0 0.3225604 0.032753 0.32604 0.32497
## IMA 100.0 0.1962299 0.029074 0.19669 0.19724
## PHB 100.0 0.1736473 0.035552 0.16318 0.16689
## PEV 74.3 0.0458205 0.032675 0.06253 0.05940
## ATM 1.5 -0.0004427 0.004661 . .
## PPI 8.6 0.0026952 0.010110 . .
## SIM 100.0 0.0869241 0.021199 0.08769 0.08849
## SBE 100.0 -0.1009979 0.024160 -0.09886 -0.09833
## EXB 100.0 0.2958414 0.033875 0.29695 0.29170
## GenderFemale 0.7 0.0003204 0.005125 . .
## OccupationFull.time.job 0.9 0.0004574 0.006291 . .
## OccupationPart.time.job 5.1 0.0067109 0.033605 . .
## OccupationRetirement 4.2 0.0067630 0.037421 . .
## OccupationNo.job 0.0 0.0000000 0.000000 . .
## OccupationHousewife 1.9 0.0023418 0.020436 . .
## OccupationOthers 0.7 -0.0008094 0.013577 . .
## EducationUndergraduate 80.1 0.1037275 0.064700 0.13373 0.13146
## EducationOthers 0.7 -0.0005549 0.009669 . .
## Income10.15millions 1.7 0.0012838 0.012454 . .
##
## nVar 9 10
## r2 0.644 0.647
## BIC -841.64076 -840.92878
## post prob 0.119 0.083
## model 3 model 4 model 5
## Intercept -0.05627 -0.15212 -0.09797
## CITYHoChiMinh . . .
## FRE2days.month.2days.week . . .
## FRE2days.year.1day.month -0.16622 . .
## FRE.2.days.year -0.31205 -0.29290 -0.28964
## TripPurposeStudying . . .
## TripPurposeShopping . 0.17783 .
## TimeUseonBusReading . . .
## TimeUseonBusTalking . . .
## TravelTime . . .
## PSAB . . .
## PSEB . . .
## PSQ 0.32641 0.32287 0.32764
## IMA 0.19642 0.19547 0.19578
## PHB 0.21128 0.16212 0.20981
## PEV . 0.06292 .
## ATM . . .
## PPI . . .
## SIM 0.08676 0.08697 0.08580
## SBE -0.09812 -0.09771 -0.09868
## EXB 0.29445 0.29629 0.30023
## GenderFemale . . .
## OccupationFull.time.job . . .
## OccupationPart.time.job . . .
## OccupationRetirement . . .
## OccupationNo.job . . .
## OccupationHousewife . . .
## OccupationOthers . . .
## EducationUndergraduate 0.13170 0.11646 0.13414
## EducationOthers . . .
## Income10.15millions . . .
##
## nVar 9 10 8
## r2 0.644 0.646 0.641
## BIC -839.87504 -839.81711 -839.78974
## post prob 0.049 0.048 0.047imageplot.bma(bma)
# Model linear regression model
attach(DataLOY)## The following objects are masked from DataLOY (pos = 3):
##
## AGE, ATM, CITY, Departure, EC_Bus, EC_Stop, Education, EXB, FRE,
## Gender, ID, IMA, Income, LOY, MarriedStatus, Occupation, PEV, PHB,
## PPA, PPI, PSAB, PSEB, PSQ, PSSS, PSSW, SAT, SBE, SIM, TimeUseonBus,
## TravelTime, TripPurpose, WC_Bus, WC_Stop## The following objects are masked from DataLOY (pos = 27):
##
## AGE, ATM, CITY, Departure, EC_Bus, EC_Stop, Education, EXB, FRE,
## Gender, ID, IMA, Income, LOY, MarriedStatus, Occupation, PEV, PHB,
## PPA, PPI, PSAB, PSEB, PSQ, PSSS, PSSW, SAT, SBE, SIM, TimeUseonBus,
## TravelTime, TripPurpose, WC_Bus, WC_Stop# Model - All variables - rempve: EC_Stop + WC_Stop + EC_Bus + WC_Bus + SAT and variable have cor > 0.7 - AGE, PPA
#DataLOY$LOY <- relevel (DataLOY$LOY, ref = "Notloyal")
m <- lm(LOY ~ PSSW + PSSS + PSAB + PSEB + PSQ + IMA + PHB + PEV + ATM + PPI + SIM + SBE + EXB + Gender + MarriedStatus + Occupation + Education + Income + CITY + FRE + TripPurpose + Departure + TimeUseonBus + TravelTime, data = DataLOY)
summary(m)##
## Call:
## lm(formula = LOY ~ PSSW + PSSS + PSAB + PSEB + PSQ + IMA + PHB +
## PEV + ATM + PPI + SIM + SBE + EXB + Gender + MarriedStatus +
## Occupation + Education + Income + CITY + FRE + TripPurpose +
## Departure + TimeUseonBus + TravelTime, data = DataLOY)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.1922 -0.3054 0.0294 0.3434 1.7183
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.101385 0.228968 -0.443 0.658032
## PSSW 0.001044 0.029409 0.035 0.971699
## PSSS 0.010754 0.026144 0.411 0.680920
## PSAB 0.020487 0.024499 0.836 0.403264
## PSEB -0.020817 0.027714 -0.751 0.452788
## PSQ 0.329068 0.038538 8.539 < 2e-16 ***
## IMA 0.203384 0.030181 6.739 2.99e-11 ***
## PHB 0.157066 0.031646 4.963 8.42e-07 ***
## PEV 0.069201 0.022786 3.037 0.002465 **
## ATM -0.052171 0.025715 -2.029 0.042792 *
## PPI 0.033701 0.017685 1.906 0.057044 .
## SIM 0.084757 0.022160 3.825 0.000141 ***
## SBE -0.110924 0.025652 -4.324 1.72e-05 ***
## EXB 0.282647 0.034762 8.131 1.55e-15 ***
## GenderFemale 0.041179 0.044409 0.927 0.354055
## MarriedStatusMarried 0.019967 0.061924 0.322 0.747198
## OccupationFull.time.job 0.163213 0.098321 1.660 0.097293 .
## OccupationPart.time.job 0.268830 0.111207 2.417 0.015847 *
## OccupationRetirement 0.311940 0.124206 2.511 0.012212 *
## OccupationNo.job 0.484454 0.346607 1.398 0.162576
## OccupationHousewife 0.261847 0.122237 2.142 0.032474 *
## OccupationOthers 0.068640 0.141210 0.486 0.627035
## EducationUndergraduate 0.080578 0.088667 0.909 0.363737
## EducationHigh.school -0.034730 0.092158 -0.377 0.706381
## EducationPostgraduate -0.050533 0.106749 -0.473 0.636064
## EducationOthers -0.112316 0.114447 -0.981 0.326692
## Income5-10millions 0.036860 0.068180 0.541 0.588906
## Income10-15millions 0.089771 0.089075 1.008 0.313833
## Income>15millions 0.052912 0.120706 0.438 0.661240
## CITYHoChiMinh -0.058281 0.050808 -1.147 0.251678
## FRE2days/month-2days/week -0.090760 0.056572 -1.604 0.109022
## FRE2days/year-1day/month -0.191370 0.075426 -2.537 0.011357 *
## FRE<2 days/year -0.334304 0.074431 -4.491 8.08e-06 ***
## TripPurposeStudying 0.140921 0.077088 1.828 0.067899 .
## TripPurposeShopping 0.090078 0.099964 0.901 0.367794
## TripPurposeEntertaining -0.008724 0.083920 -0.104 0.917228
## TripPurposeOthers 0.030321 0.083899 0.361 0.717894
## DeparturePeak-Hour 0.007923 0.044752 0.177 0.859520
## TimeUseonBusReading -0.042649 0.094165 -0.453 0.650728
## TimeUseonBusListening 0.025727 0.066809 0.385 0.700279
## TimeUseonBusNothing 0.022087 0.053872 0.410 0.681913
## TimeUseonBusTalking -0.109801 0.114634 -0.958 0.338422
## TimeUseonBusOthers 0.037826 0.136868 0.276 0.782332
## TravelTime -0.014211 0.014523 -0.979 0.328097
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.584 on 829 degrees of freedom
## Multiple R-squared: 0.6649, Adjusted R-squared: 0.6475
## F-statistic: 38.25 on 43 and 829 DF, p-value: < 2.2e-16# All variables - rempve: EC_Stop + WC_Stop + EC_Bus + WC_Bus + SAT and variable have cor > 0.7 - AGE, PPA and cor > 0.6 : PHB, PSQ, PSSW, PSAB
m3 <- lm(LOY ~ PSSS + PSEB + IMA + PEV + ATM + PPI + SIM + SBE + EXB + Gender + MarriedStatus + Occupation + Education + Income + CITY + FRE + TripPurpose + Departure + TimeUseonBus + TravelTime, data = DataLOY)
summary(m3)##
## Call:
## lm(formula = LOY ~ PSSS + PSEB + IMA + PEV + ATM + PPI + SIM +
## SBE + EXB + Gender + MarriedStatus + Occupation + Education +
## Income + CITY + FRE + TripPurpose + Departure + TimeUseonBus +
## TravelTime, data = DataLOY)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.3456 -0.2928 0.0274 0.3192 1.9636
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.123935 0.235625 0.526 0.599038
## PSSS 0.068900 0.022823 3.019 0.002615 **
## PSEB 0.080680 0.026753 3.016 0.002641 **
## IMA 0.303181 0.029762 10.187 < 2e-16 ***
## PEV 0.117258 0.020601 5.692 1.74e-08 ***
## ATM 0.006318 0.026249 0.241 0.809845
## PPI 0.037064 0.018608 1.992 0.046713 *
## SIM 0.078607 0.023270 3.378 0.000764 ***
## SBE -0.098942 0.026869 -3.682 0.000246 ***
## EXB 0.372988 0.034704 10.748 < 2e-16 ***
## GenderFemale 0.050833 0.046631 1.090 0.275980
## MarriedStatusMarried 0.047863 0.064802 0.739 0.460358
## OccupationFull.time.job 0.233748 0.102910 2.271 0.023378 *
## OccupationPart.time.job 0.331637 0.116894 2.837 0.004663 **
## OccupationRetirement 0.371421 0.130763 2.840 0.004615 **
## OccupationNo.job 0.559724 0.365566 1.531 0.126120
## OccupationHousewife 0.272852 0.128770 2.119 0.034394 *
## OccupationOthers 0.101310 0.148785 0.681 0.496112
## EducationUndergraduate 0.039324 0.093325 0.421 0.673599
## EducationHigh.school -0.054438 0.097104 -0.561 0.575209
## EducationPostgraduate -0.071184 0.112189 -0.634 0.525930
## EducationOthers -0.088108 0.120036 -0.734 0.463144
## Income5-10millions 0.008147 0.071771 0.114 0.909645
## Income10-15millions 0.037292 0.093396 0.399 0.689784
## Income>15millions 0.006831 0.126945 0.054 0.957096
## CITYHoChiMinh -0.042722 0.050979 -0.838 0.402260
## FRE2days/month-2days/week -0.081859 0.059578 -1.374 0.169821
## FRE2days/year-1day/month -0.194161 0.079380 -2.446 0.014652 *
## FRE<2 days/year -0.352869 0.078239 -4.510 7.41e-06 ***
## TripPurposeStudying 0.141869 0.081345 1.744 0.081519 .
## TripPurposeShopping 0.109622 0.105355 1.041 0.298408
## TripPurposeEntertaining 0.017462 0.088502 0.197 0.843639
## TripPurposeOthers 0.031233 0.088409 0.353 0.723969
## DeparturePeak-Hour -0.010755 0.047060 -0.229 0.819289
## TimeUseonBusReading -0.032060 0.098958 -0.324 0.746040
## TimeUseonBusListening 0.034805 0.070043 0.497 0.619380
## TimeUseonBusNothing 0.002083 0.056618 0.037 0.970660
## TimeUseonBusTalking -0.091163 0.120250 -0.758 0.448599
## TimeUseonBusOthers 0.016608 0.144218 0.115 0.908344
## TravelTime -0.023790 0.015271 -1.558 0.119656
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6164 on 833 degrees of freedom
## Multiple R-squared: 0.6249, Adjusted R-squared: 0.6073
## F-statistic: 35.58 on 39 and 833 DF, p-value: < 2.2e-16# Model 1 - Remove 2 variables non significant : Gender, Departure compare to m
m1 <- lm(LOY ~ PSSW + PSSS + PSAB + PSEB + PSQ + IMA + PHB + PEV + ATM + PPI + SIM + SBE + EXB + MarriedStatus + Occupation + Education + Income + CITY + FRE + TripPurpose + TimeUseonBus + TravelTime, data = DataLOY)
summary(m1)##
## Call:
## lm(formula = LOY ~ PSSW + PSSS + PSAB + PSEB + PSQ + IMA + PHB +
## PEV + ATM + PPI + SIM + SBE + EXB + MarriedStatus + Occupation +
## Education + Income + CITY + FRE + TripPurpose + TimeUseonBus +
## TravelTime, data = DataLOY)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.1762 -0.3031 0.0312 0.3477 1.6968
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.0648307 0.2222024 -0.292 0.770540
## PSSW 0.0004334 0.0293757 0.015 0.988233
## PSSS 0.0086879 0.0260219 0.334 0.738562
## PSAB 0.0195801 0.0244103 0.802 0.422709
## PSEB -0.0200996 0.0276840 -0.726 0.468021
## PSQ 0.3310120 0.0383505 8.631 < 2e-16 ***
## IMA 0.2034479 0.0301312 6.752 2.74e-11 ***
## PHB 0.1559343 0.0315994 4.935 9.70e-07 ***
## PEV 0.0697981 0.0227239 3.072 0.002199 **
## ATM -0.0509681 0.0256408 -1.988 0.047165 *
## PPI 0.0332411 0.0176221 1.886 0.059599 .
## SIM 0.0835412 0.0219054 3.814 0.000147 ***
## SBE -0.1123159 0.0255710 -4.392 1.27e-05 ***
## EXB 0.2842080 0.0346452 8.203 8.85e-16 ***
## MarriedStatusMarried 0.0280965 0.0612362 0.459 0.646482
## OccupationFull.time.job 0.1616708 0.0982109 1.646 0.100109
## OccupationPart.time.job 0.2660193 0.1110583 2.395 0.016827 *
## OccupationRetirement 0.3087798 0.1240724 2.489 0.013016 *
## OccupationNo.job 0.4741910 0.3454208 1.373 0.170187
## OccupationHousewife 0.2727130 0.1216073 2.243 0.025187 *
## OccupationOthers 0.0682730 0.1411143 0.484 0.628646
## EducationUndergraduate 0.0786538 0.0885800 0.888 0.374829
## EducationHigh.school -0.0325641 0.0919861 -0.354 0.723421
## EducationPostgraduate -0.0467447 0.1065746 -0.439 0.661058
## EducationOthers -0.1116478 0.1143170 -0.977 0.329026
## Income5-10millions 0.0348635 0.0680762 0.512 0.608700
## Income10-15millions 0.0780952 0.0880006 0.887 0.375099
## Income>15millions 0.0333255 0.1186741 0.281 0.778922
## CITYHoChiMinh -0.0558992 0.0506704 -1.103 0.270263
## FRE2days/month-2days/week -0.0931485 0.0564723 -1.649 0.099432 .
## FRE2days/year-1day/month -0.1947984 0.0752863 -2.587 0.009838 **
## FRE<2 days/year -0.3373366 0.0741336 -4.550 6.15e-06 ***
## TripPurposeStudying 0.1384766 0.0769840 1.799 0.072418 .
## TripPurposeShopping 0.0896948 0.0991064 0.905 0.365709
## TripPurposeEntertaining -0.0162267 0.0825642 -0.197 0.844240
## TripPurposeOthers 0.0226305 0.0833420 0.272 0.786045
## TimeUseonBusReading -0.0464313 0.0938159 -0.495 0.620788
## TimeUseonBusListening 0.0289673 0.0666326 0.435 0.663870
## TimeUseonBusNothing 0.0232029 0.0537810 0.431 0.666264
## TimeUseonBusTalking -0.1021275 0.1142656 -0.894 0.371702
## TimeUseonBusOthers 0.0421775 0.1366816 0.309 0.757717
## TravelTime -0.0149664 0.0144828 -1.033 0.301722
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.5836 on 831 degrees of freedom
## Multiple R-squared: 0.6645, Adjusted R-squared: 0.648
## F-statistic: 40.15 on 41 and 831 DF, p-value: < 2.2e-16# Model 2 - Only variables related to personal perception , remove SAT, remove cor > 0.7: PPA
m2 <- lm(LOY ~ PSSW + PSSS + PSAB + PSEB + PSQ + IMA + PHB + PEV + ATM + PPI + SIM + SBE + EXB + CITY, data = DataLOY)
summary(m2)##
## Call:
## lm(formula = LOY ~ PSSW + PSSS + PSAB + PSEB + PSQ + IMA + PHB +
## PEV + ATM + PPI + SIM + SBE + EXB + CITY, data = DataLOY)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.3876 -0.2846 0.0276 0.3267 1.7734
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.1163591 0.1855822 -0.627 0.530829
## PSSW 0.0072222 0.0294414 0.245 0.806277
## PSSS -0.0006931 0.0257829 -0.027 0.978559
## PSAB 0.0329384 0.0240887 1.367 0.171864
## PSEB -0.0205383 0.0277496 -0.740 0.459423
## PSQ 0.3313710 0.0387861 8.544 < 2e-16 ***
## IMA 0.2079326 0.0300860 6.911 9.37e-12 ***
## PHB 0.1577494 0.0313535 5.031 5.93e-07 ***
## PEV 0.0644413 0.0220538 2.922 0.003569 **
## ATM -0.0559182 0.0255124 -2.192 0.028661 *
## PPI 0.0373896 0.0175613 2.129 0.033531 *
## SIM 0.0787483 0.0219304 3.591 0.000348 ***
## SBE -0.1180293 0.0256175 -4.607 4.70e-06 ***
## EXB 0.3146558 0.0343806 9.152 < 2e-16 ***
## CITYHoChiMinh -0.0657524 0.0472890 -1.390 0.164756
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.5968 on 858 degrees of freedom
## Multiple R-squared: 0.6378, Adjusted R-squared: 0.6319
## F-statistic: 107.9 on 14 and 858 DF, p-value: < 2.2e-16# CHON 1: Model m1 - all varibles , removing : EC_Stop + WC_Stop + EC_Bus + WC_Bus + SAT and variable have cor > 0.7 - AGE, PPA and nonsignificant variables : Gender, Departure
summary(m1)##
## Call:
## lm(formula = LOY ~ PSSW + PSSS + PSAB + PSEB + PSQ + IMA + PHB +
## PEV + ATM + PPI + SIM + SBE + EXB + MarriedStatus + Occupation +
## Education + Income + CITY + FRE + TripPurpose + TimeUseonBus +
## TravelTime, data = DataLOY)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.1762 -0.3031 0.0312 0.3477 1.6968
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.0648307 0.2222024 -0.292 0.770540
## PSSW 0.0004334 0.0293757 0.015 0.988233
## PSSS 0.0086879 0.0260219 0.334 0.738562
## PSAB 0.0195801 0.0244103 0.802 0.422709
## PSEB -0.0200996 0.0276840 -0.726 0.468021
## PSQ 0.3310120 0.0383505 8.631 < 2e-16 ***
## IMA 0.2034479 0.0301312 6.752 2.74e-11 ***
## PHB 0.1559343 0.0315994 4.935 9.70e-07 ***
## PEV 0.0697981 0.0227239 3.072 0.002199 **
## ATM -0.0509681 0.0256408 -1.988 0.047165 *
## PPI 0.0332411 0.0176221 1.886 0.059599 .
## SIM 0.0835412 0.0219054 3.814 0.000147 ***
## SBE -0.1123159 0.0255710 -4.392 1.27e-05 ***
## EXB 0.2842080 0.0346452 8.203 8.85e-16 ***
## MarriedStatusMarried 0.0280965 0.0612362 0.459 0.646482
## OccupationFull.time.job 0.1616708 0.0982109 1.646 0.100109
## OccupationPart.time.job 0.2660193 0.1110583 2.395 0.016827 *
## OccupationRetirement 0.3087798 0.1240724 2.489 0.013016 *
## OccupationNo.job 0.4741910 0.3454208 1.373 0.170187
## OccupationHousewife 0.2727130 0.1216073 2.243 0.025187 *
## OccupationOthers 0.0682730 0.1411143 0.484 0.628646
## EducationUndergraduate 0.0786538 0.0885800 0.888 0.374829
## EducationHigh.school -0.0325641 0.0919861 -0.354 0.723421
## EducationPostgraduate -0.0467447 0.1065746 -0.439 0.661058
## EducationOthers -0.1116478 0.1143170 -0.977 0.329026
## Income5-10millions 0.0348635 0.0680762 0.512 0.608700
## Income10-15millions 0.0780952 0.0880006 0.887 0.375099
## Income>15millions 0.0333255 0.1186741 0.281 0.778922
## CITYHoChiMinh -0.0558992 0.0506704 -1.103 0.270263
## FRE2days/month-2days/week -0.0931485 0.0564723 -1.649 0.099432 .
## FRE2days/year-1day/month -0.1947984 0.0752863 -2.587 0.009838 **
## FRE<2 days/year -0.3373366 0.0741336 -4.550 6.15e-06 ***
## TripPurposeStudying 0.1384766 0.0769840 1.799 0.072418 .
## TripPurposeShopping 0.0896948 0.0991064 0.905 0.365709
## TripPurposeEntertaining -0.0162267 0.0825642 -0.197 0.844240
## TripPurposeOthers 0.0226305 0.0833420 0.272 0.786045
## TimeUseonBusReading -0.0464313 0.0938159 -0.495 0.620788
## TimeUseonBusListening 0.0289673 0.0666326 0.435 0.663870
## TimeUseonBusNothing 0.0232029 0.0537810 0.431 0.666264
## TimeUseonBusTalking -0.1021275 0.1142656 -0.894 0.371702
## TimeUseonBusOthers 0.0421775 0.1366816 0.309 0.757717
## TravelTime -0.0149664 0.0144828 -1.033 0.301722
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.5836 on 831 degrees of freedom
## Multiple R-squared: 0.6645, Adjusted R-squared: 0.648
## F-statistic: 40.15 on 41 and 831 DF, p-value: < 2.2e-16# According ti bma : 9 variables: FRE, PSQ, IMA, PHB, PEV, SIM, SBE, EXB, Education
m.bma <- lm(LOY ~ FRE + PSQ + IMA + PHB + PEV + SIM + SBE + EXB + Education, data = DataLOY)
summary(m.bma)##
## Call:
## lm(formula = LOY ~ FRE + PSQ + IMA + PHB + PEV + SIM + SBE +
## EXB + Education, data = DataLOY)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.14959 -0.27188 0.01943 0.33391 1.79542
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.01110 0.18183 -0.061 0.95134
## FRE2days/month-2days/week -0.06888 0.05257 -1.310 0.19046
## FRE2days/year-1day/month -0.17097 0.06498 -2.631 0.00866 **
## FRE<2 days/year -0.32979 0.06562 -5.026 6.10e-07 ***
## PSQ 0.32609 0.03218 10.133 < 2e-16 ***
## IMA 0.19743 0.02889 6.834 1.56e-11 ***
## PHB 0.16743 0.03013 5.558 3.65e-08 ***
## PEV 0.05892 0.02147 2.745 0.00618 **
## SIM 0.08531 0.02082 4.098 4.57e-05 ***
## SBE -0.09875 0.02364 -4.176 3.26e-05 ***
## EXB 0.29134 0.03375 8.633 < 2e-16 ***
## EducationUndergraduate 0.04223 0.08613 0.490 0.62401
## EducationHigh.school -0.11092 0.08473 -1.309 0.19082
## EducationPostgraduate -0.03551 0.09762 -0.364 0.71614
## EducationOthers -0.15753 0.11174 -1.410 0.15895
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.5876 on 858 degrees of freedom
## Multiple R-squared: 0.6489, Adjusted R-squared: 0.6432
## F-statistic: 113.3 on 14 and 858 DF, p-value: < 2.2e-16# CHON 2:
m.bma1 <- lm(LOY ~ FRE + PSQ + IMA + PHB + PEV + SIM + SBE + EXB + Occupation, data = DataLOY)
summary(m.bma1)##
## Call:
## lm(formula = LOY ~ FRE + PSQ + IMA + PHB + PEV + SIM + SBE +
## EXB + Occupation, data = DataLOY)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.2622 -0.2758 0.0321 0.3423 1.9313
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.008517 0.159233 -0.053 0.957355
## FRE2days/month-2days/week -0.093612 0.052768 -1.774 0.076416 .
## FRE2days/year-1day/month -0.236027 0.066365 -3.556 0.000396 ***
## FRE<2 days/year -0.356726 0.065595 -5.438 7.02e-08 ***
## PSQ 0.316324 0.032027 9.877 < 2e-16 ***
## IMA 0.205650 0.028772 7.148 1.89e-12 ***
## PHB 0.143764 0.030031 4.787 1.99e-06 ***
## PEV 0.075661 0.021587 3.505 0.000480 ***
## SIM 0.094240 0.020755 4.541 6.42e-06 ***
## SBE -0.103798 0.023588 -4.401 1.22e-05 ***
## EXB 0.273962 0.033767 8.113 1.70e-15 ***
## OccupationFull.time.job 0.110982 0.046080 2.408 0.016230 *
## OccupationPart.time.job 0.241821 0.078753 3.071 0.002204 **
## OccupationRetirement 0.284966 0.094265 3.023 0.002577 **
## OccupationNo.job 0.476977 0.341370 1.397 0.162702
## OccupationHousewife 0.268097 0.087997 3.047 0.002385 **
## OccupationOthers -0.006113 0.116588 -0.052 0.958197
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.5849 on 856 degrees of freedom
## Multiple R-squared: 0.653, Adjusted R-squared: 0.6465
## F-statistic: 100.7 on 16 and 856 DF, p-value: < 2.2e-166. Validating the importance of variables - DataLOY for 2 cities
# Based on regression coefficient
# Based on R2 of each variable according to package "relaimpo" with function calc.relimp or method of boostrap
## Relaimpo
#library(relaimpo)
#metrics <- calc.relimp(m1, type = c("lmg"))
#matrics
## Boostrap
#boot <- boot.relimp(m1, b = 10, type = c("lmg"), fixed = F)
#booteval.relimp(boot, typesel = c("lmg"), level = 0.9, bty = "perc", nodiff = T)