The expected squared-error of prediction

E(Y,ˆθ_)|x_{YˆY}2=EY|x_{Yf(θ;x_)}2Variability of Y around its conditional expected value+[f(θ;x_)Eˆθ|x_{f(ˆθ_;x_)}]2Difference between the expected value and its estimate, Squared Bias+Eˆθ_|x_[f(ˆθ_;x_)Eˆθ_|x_{f(ˆθ_;x_)}]2Change in the model due to the training data used, Variance