The following is demographic data
age <- c(34,54,67,52)
person <- c("Frank","Betty","Juan","Lisa")
sex <- c("M","F","M","F")
df <- data.frame(person,age,sex)
df## person age sex
## 1 Frank 34 M
## 2 Betty 54 F
## 3 Juan 67 M
## 4 Lisa 52 Fdf$sex <- as.factor(df$sex)
df## person age sex
## 1 Frank 34 M
## 2 Betty 54 F
## 3 Juan 67 M
## 4 Lisa 52 F#adding a column
df$smoking <- c("yes","no","no","yes")
df$smoking <- as.factor(df$smoking)
str(df)## 'data.frame': 4 obs. of 4 variables:
## $ person : chr "Frank" "Betty" "Juan" "Lisa"
## $ age : num 34 54 67 52
## $ sex : Factor w/ 2 levels "F","M": 2 1 2 1
## $ smoking: Factor w/ 2 levels "no","yes": 2 1 1 2