backtransform `scale()` for plotting

Question

I have a explanatory variable that is centered using scale() that is used to predict a response variable:

d <- data.frame(
  x=runif(100),
           


        

Answer 1

I came across this problem and I think I found a simpler solution using linear algebra.

# create matrix like object
a <- rnorm(1000,5,2)
b <- rnorm(1000,7,5) 

df <- cbind(a,b)

# get center and scaling values 
mean <- apply(df, 2, mean)
sd <- apply(df, 2, sd)

# scale data
s.df <- scale(df, center = mean, scale = sd)

#unscale data with linear algebra 
us.df <- t((t(s.df) * sd) + mean)