Smearing retransformation

From HandWiki
Revision as of 17:30, 4 August 2021 by imported>PolicyEnforcerIA (attribution)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)

The Smearing retransformation is used in regression analysis, after estimating the logarithm of a variable. Estimating the logarithm of a variable instead of the variable itself is a common technique to more closely approximate normality. In order to retransform the variable back to level from log, the Smearing retransformation is used. If the log-transformed variable y is normally distributed with mean

[math]\displaystyle{ f(X) }[/math] and variance [math]\displaystyle{ \sigma^2 }[/math]

then, the expected value of y is given by:

[math]\displaystyle{ y = \exp(f(X))\exp(\frac{1}{2}\sigma^2). }[/math]