Practice

mydata <- data.frame("ID" = c(1, 2, 3, 4),
            "Age" = c(21, 23, 18, 25),
            "Gender" = c("M", "F", "F", "M"))

print(mydata)

##   ID Age Gender
## 1  1  21      M
## 2  2  23      F
## 3  3  18      F
## 4  4  25      M

mean(mydata$Age)

## [1] 21.75

sd(mydata$Age)

## [1] 2.986079

median(mydata$Age)

## [1] 22

mydata$Height <- c(180, 171, 169, 175)

mydata$Weight <- c(75, 68, 88, 80)

Body Mass Index = Weight  Height^2

mydata$BMI <- mydata$Weight / ((mydata$Height)/100)^2

mydata2 <- mydata[c("Age", "Height")]

mydata2 <- mydata[ , c(2, 4)]

from mydata 2 - remove 3rd row

mydata3 <- mydata2[ -3 , ]

summary(mydata [ , c(-1, -3)])

##       Age            Height          Weight           BMI       
##  Min.   :18.00   Min.   :169.0   Min.   :68.00   Min.   :23.15  
##  1st Qu.:20.25   1st Qu.:170.5   1st Qu.:73.25   1st Qu.:23.23  
##  Median :22.00   Median :173.0   Median :77.50   Median :24.69  
##  Mean   :21.75   Mean   :173.8   Mean   :77.75   Mean   :25.83  
##  3rd Qu.:23.50   3rd Qu.:176.2   3rd Qu.:82.00   3rd Qu.:27.29  
##  Max.   :25.00   Max.   :180.0   Max.   :88.00   Max.   :30.81

library(pastecs)
round(stat.desc(mydata[ , c(-1, -3)]), 2)

##                Age Height Weight    BMI
## nbr.val       4.00   4.00   4.00   4.00
## nbr.null      0.00   0.00   0.00   0.00
## nbr.na        0.00   0.00   0.00   0.00
## min          18.00 169.00  68.00  23.15
## max          25.00 180.00  88.00  30.81
## range         7.00  11.00  20.00   7.66
## sum          87.00 695.00 311.00 103.34
## median       22.00 173.00  77.50  24.69
## mean         21.75 173.75  77.75  25.83
## SE.mean       1.49   2.43   4.21   1.80
## CI.mean.0.95  4.75   7.73  13.40   5.72
## var           8.92  23.58  70.92  12.91
## std.dev       2.99   4.86   8.42   3.59
## coef.var      0.14   0.03   0.11   0.14

mydataM <- mydata[mydata$Gender == "M" , ]

mydataM1 <- mydata[mydata$Gender == "M" & mydata$Age >= 20, ]