mydata <- data.frame("ID" = c(1, 2, 3, 4),
                     "Age" = c(20, 22, 18, 24),
                     "Gender" = c("M", "F", "M", "M"))
print(mydata)
##   ID Age Gender
## 1  1  20      M
## 2  2  22      F
## 3  3  18      M
## 4  4  24      M
mean(mydata$Age)
## [1] 21
sd(mydata$Age)
## [1] 2.581989

The average age of students is 21 years.

mydata$Height<- c(170, 180, 176, 177)
mydata$Weight <- c(76, 60, 72, 73)
mydata$BMI<- mydata$Weight / (mydata$Height/100)^2

Creating new dataframe, which includes only Age and Height

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

Exclude third row from mydata2

mydata3 <- mydata2[-3, ]

Descriptive statistics

summary(mydata[c(-1, -3)]  )
##       Age           Height          Weight           BMI       
##  Min.   :18.0   Min.   :170.0   Min.   :60.00   Min.   :18.52  
##  1st Qu.:19.5   1st Qu.:174.5   1st Qu.:69.00   1st Qu.:22.06  
##  Median :21.0   Median :176.5   Median :72.50   Median :23.27  
##  Mean   :21.0   Mean   :175.8   Mean   :70.25   Mean   :22.84  
##  3rd Qu.:22.5   3rd Qu.:177.8   3rd Qu.:73.75   3rd Qu.:24.05  
##  Max.   :24.0   Max.   :180.0   Max.   :76.00   Max.   :26.30

The youngest person in my sample was 18 years old.

#install.packages("pastecs")
library(pastecs)
stat.desc(mydata[ , c(-1, -3) ])
##                     Age       Height      Weight        BMI
## nbr.val       4.0000000   4.00000000   4.0000000  4.0000000
## nbr.null      0.0000000   0.00000000   0.0000000  0.0000000
## nbr.na        0.0000000   0.00000000   0.0000000  0.0000000
## min          18.0000000 170.00000000  60.0000000 18.5185185
## max          24.0000000 180.00000000  76.0000000 26.2975779
## range         6.0000000  10.00000000  16.0000000  7.7790593
## sum          84.0000000 703.00000000 281.0000000 91.3609929
## median       21.0000000 176.50000000  72.5000000 23.2724482
## mean         21.0000000 175.75000000  70.2500000 22.8402482
## SE.mean       1.2909944   2.09662427   3.5207717  1.6074232
## CI.mean.0.95  4.1085205   6.67239416  11.2046669  5.1155379
## var           6.6666667  17.58333333  49.5833333 10.3352369
## std.dev       2.5819889   4.19324854   7.0415434  3.2148463
## coef.var      0.1229519   0.02385917   0.1002355  0.1407536
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          18.00 170.00  60.00 18.52
## max          24.00 180.00  76.00 26.30
## range         6.00  10.00  16.00  7.78
## sum          84.00 703.00 281.00 91.36
## median       21.00 176.50  72.50 23.27
## mean         21.00 175.75  70.25 22.84
## SE.mean       1.29   2.10   3.52  1.61
## CI.mean.0.95  4.11   6.67  11.20  5.12
## var           6.67  17.58  49.58 10.34
## std.dev       2.58   4.19   7.04  3.21
## coef.var      0.12   0.02   0.10  0.14
mydata_M <- mydata[ mydata$Gender == "M" ,  ]
mydata_M1 <- mydata[ mydata$Gender == "M" & mydata$Age >= 20 ,  ]