z-score-scale.R

#z-score

#create vector of data
data <- c(6, 7, 7, 12, 13, 13, 15, NA, 19, 22)
#find z-score for each data value 
z_scores <- (data-mean(data, na.rm = T))/sd(data, na.rm = T)
#display z-scores 
z_scores

##  [1] -1.21212121 -1.03030303 -1.03030303 -0.12121212  0.06060606  0.06060606
##  [7]  0.42424242          NA  1.15151515  1.69696970

data.frame(scale(data))

##    scale.data.
## 1  -1.21212121
## 2  -1.03030303
## 3  -1.03030303
## 4  -0.12121212
## 5   0.06060606
## 6   0.06060606
## 7   0.42424242
## 8           NA
## 9   1.15151515
## 10  1.69696970

#create dataframe
df <- data.frame(assists = c(4, 4, 6, 7, 9, 13),
                 points = c(24, NA, 13, 15, 19, 22),
                 rebounds = c(5, 5, 7, 8, 14, 15))

#find z-scores of each column
sapply(df, function(df) (df-mean(df, na.rm = T))/sd(df, na.rm = T))

##          assists      points   rebounds
## [1,] -0.92315712  1.17004875 -0.9035079
## [2,] -0.92315712          NA -0.9035079
## [3,] -0.34011052 -1.21338389 -0.4517540
## [4,] -0.04858722 -0.78003250 -0.2258770
## [5,]  0.53445939  0.08667028  1.1293849
## [6,]  1.70055260  0.73669736  1.3552619

scale(df)

##          assists      points   rebounds
## [1,] -0.92315712  1.17004875 -0.9035079
## [2,] -0.92315712          NA -0.9035079
## [3,] -0.34011052 -1.21338389 -0.4517540
## [4,] -0.04858722 -0.78003250 -0.2258770
## [5,]  0.53445939  0.08667028  1.1293849
## [6,]  1.70055260  0.73669736  1.3552619
## attr(,"scaled:center")
##   assists    points  rebounds 
##  7.166667 18.600000  9.000000 
## attr(,"scaled:scale")
##  assists   points rebounds 
## 3.430258 4.615192 4.427189

#ref  https://www.statology.org/z-score-r/