Linear Transformation of Random Variables

Y = aX + b

i.i.d. = “independent and identically distributed”

  • Y will have the same distribution shape as X.

    • If X has a normal distribution then Y will also be normally distributed.

    • If X has a discrete probability distribution, the corresponding values of Y will also have the same probabilities

New…

y = X + b

y = a * X

y = a * X + b

…Mean

μ(y) = μ(X) + b

μ(y) = a * μ(X)

μ(y) = a * μ(X) + b

…Standard Deviation

σ(y) = σ(X)

σ(y) = a * σ(X)

σ(y) = a * σ(X)

…Variance

σ²(y) = σ²(X)

σ²(y) = a² * σ²(X)

σ²(y) = a² * σ²(X)