Untitled

titanic.df<-read.csv("Titanic Data.csv", sep = ",")
View(titanic.df)

dim(titanic.df)

## [1] 889   8

summary(titanic.df)

##     Survived          Pclass          Sex           Age       
##  Min.   :0.0000   Min.   :1.000   female:312   Min.   : 0.40  
##  1st Qu.:0.0000   1st Qu.:2.000   male  :577   1st Qu.:22.00  
##  Median :0.0000   Median :3.000                Median :29.70  
##  Mean   :0.3825   Mean   :2.312                Mean   :29.65  
##  3rd Qu.:1.0000   3rd Qu.:3.000                3rd Qu.:35.00  
##  Max.   :1.0000   Max.   :3.000                Max.   :80.00  
##      SibSp            Parch             Fare         Embarked
##  Min.   :0.0000   Min.   :0.0000   Min.   :  0.000   C:168   
##  1st Qu.:0.0000   1st Qu.:0.0000   1st Qu.:  7.896   Q: 77   
##  Median :0.0000   Median :0.0000   Median : 14.454   S:644   
##  Mean   :0.5242   Mean   :0.3825   Mean   : 32.097           
##  3rd Qu.:1.0000   3rd Qu.:0.0000   3rd Qu.: 31.000           
##  Max.   :8.0000   Max.   :6.0000   Max.   :512.329

mytable<-table(titanic.df$Survived==1)
addmargins(mytable)

## 
## FALSE  TRUE   Sum 
##   549   340   889

prop<-prop.table(mytable)
100*prop

## 
##    FALSE     TRUE 
## 61.75478 38.24522

mytable2<- table(titanic.df$Pclass==1,titanic.df$Survived==1)
addmargins(mytable2)

##        
##         FALSE TRUE Sum
##   FALSE   469  206 675
##   TRUE     80  134 214
##   Sum     549  340 889

prop1<- prop.table(mytable2)
100*prop1

##        
##             FALSE      TRUE
##   FALSE 52.755906 23.172103
##   TRUE   8.998875 15.073116

mytable3<- table(titanic.df$Survived==1,titanic.df$Pclass==1,titanic.df$Sex)
addmargins(mytable3)

## , ,  = female
## 
##        
##         FALSE TRUE Sum
##   FALSE    78    3  81
##   TRUE    142   89 231
##   Sum     220   92 312
## 
## , ,  = male
## 
##        
##         FALSE TRUE Sum
##   FALSE   391   77 468
##   TRUE     64   45 109
##   Sum     455  122 577
## 
## , ,  = Sum
## 
##        
##         FALSE TRUE Sum
##   FALSE   469   80 549
##   TRUE    206  134 340
##   Sum     675  214 889

surviversBySex <- xtabs(~ Survived + Sex, data=titanic.df)
chisq.test(surviversBySex)

## 
##  Pearson's Chi-squared test with Yates' continuity correction
## 
## data:  surviversBySex
## X-squared = 258.43, df = 1, p-value < 2.2e-16

(chisq.test(surviversBySex))$p.value

## [1] 3.77991e-58