Sameer Mahur
patientID <- c(1, 2, 3, 4)
age <- c(25, 34, 28, 52)
diabetes <- c("Type1", "Type2", "Type1", "Type1")
status <- c("Poor", "Improved", "Excellent", "Poor")
diabetes <- factor(diabetes)
status <- factor(status, order=TRUE)
patientdata <- data.frame(patientID, age, diabetes, status)
# structure of the patientdata
str(patientdata)
'data.frame': 4 obs. of 4 variables:
$ patientID: num 1 2 3 4
$ age : num 25 34 28 52
$ diabetes : Factor w/ 2 levels "Type1","Type2": 1 2 1 1
$ status : Ord.factor w/ 3 levels "Excellent"<"Improved"<..: 3 2 1 3
# summary
summary(patientdata)
patientID age diabetes status
Min. :1.00 Min. :25.00 Type1:3 Excellent:1
1st Qu.:1.75 1st Qu.:27.25 Type2:1 Improved :1
Median :2.50 Median :31.00 Poor :2
Mean :2.50 Mean :34.75
3rd Qu.:3.25 3rd Qu.:38.50
Max. :4.00 Max. :52.00