### DESCRIPTIVE STATISTICS ###
#how many motorcyclists vs car drivers?
janitor::tabyl(mydata$vehicle.f)
## mydata$vehicle.f n percent valid_percent
## motorcyclists 194 0.50129199 0.5159574
## car drivers 182 0.47028424 0.4840426
## <NA> 11 0.02842377 NA
descriptives(mydata, vars = vars(mhc, ss), missing = TRUE)
##
## DESCRIPTIVES
##
## Descriptives
## ───────────────────────────────────────────────
## mhc ss
## ───────────────────────────────────────────────
## N 319 387
## Missing 68 0
## Mean 4.033260 15.50904
## Median 4.071429 18
## Standard deviation 0.9326433 9.841058
## Minimum 1.142857 0
## Maximum 6.000000 35
## ───────────────────────────────────────────────
descriptives(mydata, vars = vars(openness, extraversion, agreeableness, conscientiousness, neuroticism), missing = TRUE)
##
## DESCRIPTIVES
##
## Descriptives
## ────────────────────────────────────────────────────────────────────────────────────────────────────────
## openness extraversion agreeableness conscientiousness neuroticism
## ────────────────────────────────────────────────────────────────────────────────────────────────────────
## N 329 329 329 329 328
## Missing 58 58 58 58 59
## Mean 4.451476 4.420810 4.614573 4.601860 3.768427
## Median 4.375000 4.375000 4.555556 4.444444 3.888889
## Standard deviation 0.8442381 0.7682969 0.9370719 0.6621849 0.8382753
## Minimum 2.000000 2.125000 2.222222 2.888889 1.125000
## Maximum 6.888889 6.500000 7.000000 6.625000 5.875000
## ────────────────────────────────────────────────────────────────────────────────────────────────────────
descriptives(mydata, vars = vars(hours.ride, years.riding, near.crashes), missing = TRUE)
##
## DESCRIPTIVES
##
## Descriptives
## ────────────────────────────────────────────────────────────────────
## hours.ride years.riding near.crashes
## ────────────────────────────────────────────────────────────────────
## N 157 162 157
## Missing 230 225 230
## Mean 16.12739 14.64198 8.159236
## Median 12 9.000000 3
## Standard deviation 12.35673 14.22561 15.98738
## Minimum 1 0 0
## Maximum 70 56 100
## ────────────────────────────────────────────────────────────────────
janitor::tabyl(mydata$ethnicity.f)
## mydata$ethnicity.f n percent valid_percent
## white 343 0.88630491 0.93715847
## asian 18 0.04651163 0.04918033
## black 5 0.01291990 0.01366120
## indigenous 0 0.00000000 0.00000000
## <NA> 21 0.05426357 NA
janitor::tabyl(mydata$income.f)
## mydata$income.f n percent valid_percent
## under $20k/year 41 0.1059432 0.2113402
## $20-$40k/year 39 0.1007752 0.2010309
## $40-$60k/year 57 0.1472868 0.2938144
## $60-$80k/year 57 0.1472868 0.2938144
## $80-$100k/year 0 0.0000000 0.0000000
## over $100k/year 0 0.0000000 0.0000000
## <NA> 193 0.4987080 NA
janitor::tabyl(mydata$gender.f)
## mydata$gender.f n percent valid_percent
## woman 193 0.498708010 0.51193634
## men 182 0.470284238 0.48275862
## non-binary 2 0.005167959 0.00530504
## <NA> 10 0.025839793 NA
janitor::tabyl(mydata$gear.f)
## mydata$gear.f n percent valid_percent
## wears full gear 133 0.3436693 0.8209877
## wears partial goal 29 0.0749354 0.1790123
## <NA> 225 0.5813953 NA
janitor::tabyl(mydata$checks.f)
## mydata$checks.f n percent valid_percent
## always 120 0.310077519 0.74534161
## usually 34 0.087855297 0.21118012
## sometimes 4 0.010335917 0.02484472
## rarely 1 0.002583979 0.00621118
## never 2 0.005167959 0.01242236
## <NA> 226 0.583979328 NA
janitor::tabyl(mydata$passenger.f)
## mydata$passenger.f n percent valid_percent
## always 1 0.002583979 0.00621118
## usually 11 0.028423773 0.06832298
## sometimes 32 0.082687339 0.19875776
## rarely 50 0.129198966 0.31055901
## never 67 0.173126615 0.41614907
## <NA> 226 0.583979328 NA
janitor::tabyl(mydata$speed.f)
## mydata$speed.f n percent valid_percent
## highway 22 0.05684755 0.1358025
## backroads 140 0.36175711 0.8641975
## <NA> 225 0.58139535 NA
janitor::tabyl(mydata$style.f)
## mydata$style.f n percent valid_percent
## sport 93 0.2403101 0.5776398
## cruiser 68 0.1757106 0.4223602
## <NA> 226 0.5839793 NA
janitor::tabyl(mydata$accident.f)
## mydata$accident.f n percent valid_percent
## been in accident 50 0.1291990 0.308642
## no accidents 112 0.2894057 0.691358
## <NA> 225 0.5813953 NA
janitor::tabyl(mydata$safety.f)
## mydata$safety.f n percent valid_percent
## safety course 136 0.35142119 0.8395062
## no course 26 0.06718346 0.1604938
## <NA> 225 0.58139535 NA
janitor::tabyl(mydata$limit.f)
## mydata$limit.f n percent valid_percent
## always 18 0.046511628 0.11042945
## usually 44 0.113695090 0.26993865
## sometimes 68 0.175710594 0.41717791
## rarely 30 0.077519380 0.18404908
## never 3 0.007751938 0.01840491
## <NA> 224 0.578811370 NA
#looking at key variables by group
tapply(mydata$conscientiousness, mydata$vehicle.f, summary)
## $motorcyclists
## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 2.889 4.667 5.111 5.046 5.444 6.625 30
##
## $`car drivers`
## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 3.000 4.000 4.111 4.161 4.333 5.000 17
tapply(mydata$openness, mydata$vehicle.f, summary)
## $motorcyclists
## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 3.000 4.667 5.000 5.049 5.444 6.889 30
##
## $`car drivers`
## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 2.000 3.500 3.875 3.858 4.125 5.500 17
tapply(mydata$agreeableness, mydata$vehicle.f, summary)
## $motorcyclists
## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 3.000 4.778 5.222 5.237 5.778 7.000 30
##
## $`car drivers`
## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 2.222 3.667 4.000 3.996 4.333 6.667 17
tapply(mydata$extraversion, mydata$vehicle.f, summary)
## $motorcyclists
## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 2.125 3.844 4.375 4.425 5.031 6.500 30
##
## $`car drivers`
## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 2.125 4.000 4.375 4.417 4.750 5.750 17
tapply(mydata$neuroticism, mydata$vehicle.f, summary)
## $motorcyclists
## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 1.125 2.625 3.625 3.474 4.125 5.875 30
##
## $`car drivers`
## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 2.125 3.778 4.000 4.063 4.333 5.222 18
tapply(mydata$ss.disinhib, mydata$vehicle.f, summary)
## $motorcyclists
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.00 0.00 4.00 3.49 6.00 9.00
##
## $`car drivers`
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.000 2.000 4.000 4.077 6.000 10.000
tapply(mydata$ss.boredom, mydata$vehicle.f, summary)
## $motorcyclists
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.000 0.000 2.000 1.964 3.000 9.000
##
## $`car drivers`
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.00 0.00 1.00 1.72 2.75 9.00
tapply(mydata$ss.experience, mydata$vehicle.f, summary)
## $motorcyclists
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.000 0.000 5.000 4.351 7.000 10.000
##
## $`car drivers`
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.000 3.000 5.000 4.764 7.000 10.000
tapply(mydata$ss.thrill, mydata$vehicle.f, summary)
## $motorcyclists
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.000 0.000 6.000 5.108 8.000 10.000
##
## $`car drivers`
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.000 1.250 5.000 4.621 7.000 10.000
tapply(mydata$mhc, mydata$vehicle.f, summary)
## $motorcyclists
## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 1.143 3.500 4.286 4.120 4.786 6.000 36
##
## $`car drivers`
## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 1.786 3.286 4.000 3.948 4.643 5.786 21
#########################################################################################################
# t-tests to see if there are differences by vehicle driver group
#########################################################################################################
tapply(mydata$ss, mydata$vehicle.f, summary)
## $motorcyclists
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.00 0.00 19.00 15.76 24.00 35.00
##
## $`car drivers`
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.00 11.00 18.00 16.18 23.00 32.00
#motorcyclists have lower ss (15.76) than car (16.18)
w1 <- wilcox.test(ss ~ vehicle, data = mydata, exact = FALSE)
w1
##
## Wilcoxon rank sum test with continuity correction
##
## data: ss by vehicle
## W = 18284, p-value = 0.5476
## alternative hypothesis: true location shift is not equal to 0
#not significantly different
#########################################################################################################
tapply(mydata$ss.disinhib, mydata$vehicle.f, summary)
## $motorcyclists
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.00 0.00 4.00 3.49 6.00 9.00
##
## $`car drivers`
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.000 2.000 4.000 4.077 6.000 10.000
#motorcyclists have lower ss.disinh (3.49) than car (4.08)
w2 <- wilcox.test(ss.disinhib ~ vehicle.f, data = mydata, exact = FALSE)
w2 # significantly different
##
## Wilcoxon rank sum test with continuity correction
##
## data: ss.disinhib by vehicle.f
## W = 15543, p-value = 0.0429
## alternative hypothesis: true location shift is not equal to 0
#########################################################################################################
tapply(mydata$ss.thrill, mydata$vehicle.f, summary)
## $motorcyclists
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.000 0.000 6.000 5.108 8.000 10.000
##
## $`car drivers`
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.000 1.250 5.000 4.621 7.000 10.000
#motorcyclists have lower ss.thill (5.11) than car (4.62)
w3 <- wilcox.test(ss.thrill ~ vehicle.f, data = mydata, exact = FALSE)
w3 #not different
##
## Wilcoxon rank sum test with continuity correction
##
## data: ss.thrill by vehicle.f
## W = 19140, p-value = 0.1545
## alternative hypothesis: true location shift is not equal to 0
#########################################################################################################
tapply(mydata$ss.experience, mydata$vehicle.f, summary)
## $motorcyclists
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.000 0.000 5.000 4.351 7.000 10.000
##
## $`car drivers`
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.000 3.000 5.000 4.764 7.000 10.000
#motorcyclists have lower ss.exp (4.35) than car (4.76)
w4 <- wilcox.test(ss.experience ~ vehicle.f, data = mydata, exact = FALSE)
w4 #not different
##
## Wilcoxon rank sum test with continuity correction
##
## data: ss.experience by vehicle.f
## W = 16681, p-value = 0.351
## alternative hypothesis: true location shift is not equal to 0
#########################################################################################################
tapply(mydata$mhc, mydata$vehicle.f, summary)
## $motorcyclists
## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 1.143 3.500 4.286 4.120 4.786 6.000 36
##
## $`car drivers`
## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 1.786 3.286 4.000 3.948 4.643 5.786 21
#motorcyclists have higher well-being (4.12) than car (3.95)
w5 <- wilcox.test(mhc ~ vehicle.f, data = mydata, exact = FALSE)
w5 #not different
##
## Wilcoxon rank sum test with continuity correction
##
## data: mhc by vehicle.f
## W = 14247, p-value = 0.06355
## alternative hypothesis: true location shift is not equal to 0
#########################################################################################################
tapply(mydata$extraversion, mydata$vehicle.f, summary)
## $motorcyclists
## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 2.125 3.844 4.375 4.425 5.031 6.500 30
##
## $`car drivers`
## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 2.125 4.000 4.375 4.417 4.750 5.750 17
#motorcyclists have higher extraversion (4.43) than car (4.42)
w6 <- wilcox.test(extraversion ~ vehicle.f, data = mydata, exact = FALSE)
w6 #not different
##
## Wilcoxon rank sum test with continuity correction
##
## data: extraversion by vehicle.f
## W = 13297, p-value = 0.7872
## alternative hypothesis: true location shift is not equal to 0
#########################################################################################################
tapply(mydata$openness, mydata$vehicle.f, summary)
## $motorcyclists
## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 3.000 4.667 5.000 5.049 5.444 6.889 30
##
## $`car drivers`
## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 2.000 3.500 3.875 3.858 4.125 5.500 17
#motorcyclists have higher openness (5.05) than car (3.86)
w7 <- wilcox.test(openness ~ vehicle.f, data = mydata, exact = FALSE)
w7 #sig different
##
## Wilcoxon rank sum test with continuity correction
##
## data: openness by vehicle.f
## W = 24968, p-value < 2.2e-16
## alternative hypothesis: true location shift is not equal to 0
########################################################################################################
tapply(mydata$neuroticism, mydata$vehicle.f, summary)
## $motorcyclists
## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 1.125 2.625 3.625 3.474 4.125 5.875 30
##
## $`car drivers`
## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 2.125 3.778 4.000 4.063 4.333 5.222 18
#motorcyclists have lower openness (3.48) than car (4.06)
w8 <- wilcox.test(neuroticism ~ vehicle.f, data = mydata, exact = FALSE)
w8 #sig different
##
## Wilcoxon rank sum test with continuity correction
##
## data: neuroticism by vehicle.f
## W = 8177.5, p-value = 8.14e-10
## alternative hypothesis: true location shift is not equal to 0
########################################################################################################
tapply(mydata$agreeableness, mydata$vehicle.f, summary)
## $motorcyclists
## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 3.000 4.778 5.222 5.237 5.778 7.000 30
##
## $`car drivers`
## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 2.222 3.667 4.000 3.996 4.333 6.667 17
#motorcyclists have higher agreeableness (5.24) than car (4.0)
w9 <- wilcox.test(agreeableness ~ vehicle.f, data = mydata, exact = FALSE)
w9 #sig different
##
## Wilcoxon rank sum test with continuity correction
##
## data: agreeableness by vehicle.f
## W = 24110, p-value < 2.2e-16
## alternative hypothesis: true location shift is not equal to 0
########################################################################################################
tapply(mydata$conscientiousness, mydata$vehicle.f, summary)
## $motorcyclists
## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 2.889 4.667 5.111 5.046 5.444 6.625 30
##
## $`car drivers`
## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 3.000 4.000 4.111 4.161 4.333 5.000 17
#motorcyclists have higher conscientiousness (5.05) than car (4.16)
w10 <- wilcox.test(conscientiousness ~ vehicle.f, data = mydata, exact = FALSE)
w10 #sig different
##
## Wilcoxon rank sum test with continuity correction
##
## data: conscientiousness by vehicle.f
## W = 24394, p-value < 2.2e-16
## alternative hypothesis: true location shift is not equal to 0
#########################################################################################################
