Exercise 2.3 The dataset UCBAdmissions is a 3-way table of frequencies classified by Admit, Gender, and Department
sum(UCBAdmissions)
## [1] 4526
Therefore, the total number of cases is 4526
margin.table(UCBAdmissions, margin = 3)
## Dept
## A B C D E F
## 933 585 918 792 584 714
There are 933, 585,918,792,584 and 714 applicants for the departments A to F.
c.For each department, find the overall proportion of applicants who were admitted.
prop.table(ftable(UCBAdmissions,row.vars = "Admit", col.vars = "Dept"))
## Dept A B C D E F
## Admit
## Admitted 0.13278833 0.08174989 0.07114450 0.05943438 0.03247901 0.01016350
## Rejected 0.07335395 0.04750331 0.13168361 0.11555457 0.09655325 0.14759169
prop.table(ftable(UCBAdmissions,row.vars = "Admit",col.vars = "Dept")[,1])
## [1] 0.6441586 0.3558414
For department A, the admit percentage is 64.4% and rejection rate is 7.33%
prop.table(ftable(UCBAdmissions,row.vars = "Admit",col.vars = "Dept")[,2])
## [1] 0.6324786 0.3675214
prop.table(ftable(UCBAdmissions,row.vars = "Admit",col.vars = "Dept")[,3])
## [1] 0.3507625 0.6492375
For department C, the admit percentage is 35% and rejection rate is 64.9%
prop.table(ftable(UCBAdmissions,row.vars = "Admit",col.vars = "Dept")[,4])
## [1] 0.3396465 0.6603535
For department D, the admit percentage is 39.9% and rejection rate is 66%
prop.table(ftable(UCBAdmissions,row.vars = "Admit",col.vars = "Dept")[,5])
## [1] 0.2517123 0.7482877
For department E, the admit percentage is 25.17% and rejection rate is 74.8%
prop.table(ftable(UCBAdmissions,row.vars = "Admit",col.vars = "Dept")[,6])
## [1] 0.06442577 0.93557423
For department F, the admit percentage is 6.44% and rejection rate is 93.5%
tableA <- aperm(UCBAdmissions, c(3,2,1))
tableA
## , , Admit = Admitted
##
## Gender
## Dept Male Female
## A 512 89
## B 353 17
## C 120 202
## D 138 131
## E 53 94
## F 22 24
##
## , , Admit = Rejected
##
## Gender
## Dept Male Female
## A 313 19
## B 207 8
## C 205 391
## D 279 244
## E 138 299
## F 351 317
table1 <-tableA[,,"Admitted"]
table2 <-tableA[,,"Rejected"]
tableB <- table1/(table1+table2)
tableB
## Gender
## Dept Male Female
## A 0.62060606 0.82407407
## B 0.63035714 0.68000000
## C 0.36923077 0.34064081
## D 0.33093525 0.34933333
## E 0.27748691 0.23918575
## F 0.05898123 0.07038123
The above table provide proportion of men who are admitted in each department. For department A, 62% male candidates and 82.4% female candidates. For department B, 63% male candidates and 68% female candidates For department C, 37% male candidates and 34% female candidates For department D, 33% male candidates and 35% female candidates For department E, 28% male candidates and 24% female candidates For department F, 5.8% male candidates and 7% female candidates
Exercise 2.5 The dataset UKSoccer in vcd gives the distributions of number of goals scored by the 20 teams in the 1995/96 season of the Premier League of the UK Football Association
data("UKSoccer",package="vcd")
ftable(UKSoccer)
## Away 0 1 2 3 4
## Home
## 0 27 29 10 8 2
## 1 59 53 14 12 4
## 2 28 32 14 12 4
## 3 19 14 7 4 1
## 4 7 8 10 2 0
sum(UKSoccer)
## [1] 380
addmargins(UKSoccer)
## Away
## Home 0 1 2 3 4 Sum
## 0 27 29 10 8 2 76
## 1 59 53 14 12 4 142
## 2 28 32 14 12 4 90
## 3 19 14 7 4 1 45
## 4 7 8 10 2 0 27
## Sum 140 136 55 38 11 380
The marginal total for the home teams are 76,142,90,45, and 27 for 0,1,2,3,4+ respectively. Similarly, the marginal total for away teams are 140,136,55,38, and 11 for 0,1,2,3,4+ goals respectively.
prop.table(addmargins(UKSoccer))
## Away
## Home 0 1 2 3 4
## 0 0.0177631579 0.0190789474 0.0065789474 0.0052631579 0.0013157895
## 1 0.0388157895 0.0348684211 0.0092105263 0.0078947368 0.0026315789
## 2 0.0184210526 0.0210526316 0.0092105263 0.0078947368 0.0026315789
## 3 0.0125000000 0.0092105263 0.0046052632 0.0026315789 0.0006578947
## 4 0.0046052632 0.0052631579 0.0065789474 0.0013157895 0.0000000000
## Sum 0.0921052632 0.0894736842 0.0361842105 0.0250000000 0.0072368421
## Away
## Home Sum
## 0 0.0500000000
## 1 0.0934210526
## 2 0.0592105263
## 3 0.0296052632
## 4 0.0177631579
## Sum 0.2500000000
From this table, we can deduce that there is 30% chance that that home team makes 3 goals in its matches.