Mean squared error

If a vector of ${\displaystyle n}$ predictions is generated from a sample of ${\displaystyle n}$ data points on all variables, and ${\displaystyle Y}$ is the vector of observed values of the variable being predicted, with ${\displaystyle {\hat {Y}}}$ being the predicted values (e.g. as from a least-squares fit), then the within-sample MSE of the predictor is computed as

${\displaystyle \operatorname {MSE} ={\frac {1}{n}}\sum _{i=1}^{n}\left(Y_{i}-{\hat {Y_{i}}}\right)^{2}.}$

In other words, the MSE is the mean ${\textstyle \left({\frac {1}{n}}\sum _{i=1}^{n}\right)}$ of the squares of the errors ${\textstyle \left(Y_{i}-{\hat {Y_{i}}}\right)^{2}}$. This is an easily computable quantity for a particular sample (and hence is sample-dependent).

In matrix notation,

${\displaystyle \operatorname {MSE} ={\frac {1}{n}}\sum _{i=1}^{n}(e_{i})^{2}={\frac {1}{n}}\mathbf {e} ^{\mathsf {T}}\mathbf {e} }$

where ${\displaystyle e_{i}}$ is ${\displaystyle (Y_{i}-{\hat {Y_{i}}})}$ and ${\displaystyle \mathbf {e} }$ is a ${\displaystyle n\times 1}$ column vector.

The MSE can also be computed on q data points that were not used in estimating the model, either because they were held back for this purpose, or because these data have been newly obtained. Within this process, known as cross-validation, the MSE is often called the test MSE,[4] and is computed as

${\displaystyle \operatorname {MSE} ={\frac {1}{q}}\sum _{i=n+1}^{n+q}\left(Y_{i}-{\hat {Y_{i}}}\right)^{2}.}$

The MSE of an estimator ${\displaystyle {\hat {\theta }}}$ with respect to an unknown parameter ${\displaystyle \theta }$ is defined as[1]

${\displaystyle \operatorname {MSE} ({\hat {\theta }})=\operatorname {E} _{\theta }\left[({\hat {\theta }}-\theta )^{2}\right].}$

This definition depends on the unknown parameter, but the MSE is a priori a property of an estimator. The MSE could be a function of unknown parameters, in which case any estimator of the MSE based on estimates of these parameters would be a function of the data (and thus a random variable). If the estimator ${\displaystyle {\hat {\theta }}}$ is derived as a sample statistic and is used to estimate some population parameter, then the expectation is with respect to the sampling distribution of the sample statistic.

The MSE can be written as the sum of the variance of the estimator and the squared bias of the estimator, providing a useful way to calculate the MSE and implying that in the case of unbiased estimators, the MSE and variance are equivalent.[5]

${\displaystyle \operatorname {MSE} ({\hat {\theta }})=\operatorname {Var} _{\theta }({\hat {\theta }})+\operatorname {Bias} ({\hat {\theta }},\theta )^{2}.}$

${\displaystyle {\begin{aligned}\operatorname {MSE} ({\hat {\theta }})&=\operatorname {E} _{\theta }\left[({\hat {\theta }}-\theta )^{2}\right]\\&=\operatorname {E} _{\theta }\left[\left({\hat {\theta }}-\operatorname {E} _{\theta }[{\hat {\theta }}]+\operatorname {E} _{\theta }[{\hat {\theta }}]-\theta \right)^{2}\right]\\&=\operatorname {E} _{\theta }\left[\left({\hat {\theta }}-\operatorname {E} _{\theta }[{\hat {\theta }}]\right)^{2}+2\left({\hat {\theta }}-\operatorname {E} _{\theta }[{\hat {\theta }}]\right)\left(\operatorname {E} _{\theta }[{\hat {\theta }}]-\theta \right)+\left(\operatorname {E} _{\theta }[{\hat {\theta }}]-\theta \right)^{2}\right]\\&=\operatorname {E} _{\theta }\left[\left({\hat {\theta }}-\operatorname {E} _{\theta }[{\hat {\theta }}]\right)^{2}\right]+\operatorname {E} _{\theta }\left[2\left({\hat {\theta }}-\operatorname {E} _{\theta }[{\hat {\theta }}]\right)\left(\operatorname {E} _{\theta }[{\hat {\theta }}]-\theta \right)\right]+\operatorname {E} _{\theta }\left[\left(\operatorname {E} _{\theta }[{\hat {\theta }}]-\theta \right)^{2}\right]\\&=\operatorname {E} _{\theta }\left[\left({\hat {\theta }}-\operatorname {E} _{\theta }[{\hat {\theta }}]\right)^{2}\right]+2\left(\operatorname {E} _{\theta }[{\hat {\theta }}]-\theta \right)\operatorname {E} _{\theta }\left[{\hat {\theta }}-\operatorname {E} _{\theta }[{\hat {\theta }}]\right]+\left(\operatorname {E} _{\theta }[{\hat {\theta }}]-\theta \right)^{2}&&\operatorname {E} _{\theta }[{\hat {\theta }}]-\theta ={\text{const.}}\\&=\operatorname {E} _{\theta }\left[\left({\hat {\theta }}-\operatorname {E} _{\theta }[{\hat {\theta }}]\right)^{2}\right]+2\left(\operatorname {E} _{\theta }[{\hat {\theta }}]-\theta \right)\left(\operatorname {E} _{\theta }[{\hat {\theta }}]-\operatorname {E} _{\theta }[{\hat {\theta }}]\right)+\left(\operatorname {E} _{\theta }[{\hat {\theta }}]-\theta \right)^{2}&&\operatorname {E} _{\theta }[{\hat {\theta }}]={\text{const.}}\\&=\operatorname {E} _{\theta }\left[\left({\hat {\theta }}-\operatorname {E} _{\theta }[{\hat {\theta }}]\right)^{2}\right]+\left(\operatorname {E} _{\theta }[{\hat {\theta }}]-\theta \right)^{2}\\&=\operatorname {Var} _{\theta }({\hat {\theta }})+\operatorname {Bias} _{\theta }({\hat {\theta }},\theta )^{2}\end{aligned}}}$

An even shorter proof can be achieved using the well-known formula that for a random variable ${\textstyle X}$, ${\textstyle \mathbb {E} (X^{2})=\operatorname {Var} (X)+(\mathbb {E} (X))^{2}}$. By substituting ${\textstyle X}$ with, ${\textstyle {\hat {\theta }}-\theta }$, we have

$${\displaystyle {\begin{aligned}\operatorname {MSE} ({\hat {\theta }})&=\mathbb {E} [({\hat {\theta }}-\theta )^{2}]\\&=\operatorname {Var} ({\hat {\theta }}-\theta )+(\mathbb {E} [{\hat {\theta }}-\theta ])^{2}\\&=\operatorname {Var} ({\hat {\theta }})+\operatorname {Bias} ^{2}({\hat {\theta }},\theta )\end{aligned}}}$$

But in real modeling case, MSE could be described as the addition of model variance, model bias, and irreducible uncertainty (see Bias–variance tradeoff). According to the relationship, the MSE of the estimators could be simply used for the efficiency comparison, which includes the information of estimator variance and bias. This is called MSE criterion.

Suppose we have a random sample of size ${\displaystyle n}$ from a population, ${\displaystyle X_{1},\dots ,X_{n}}$. Suppose the sample units were chosen with replacement. That is, the ${\displaystyle n}$ units are selected one at a time, and previously selected units are still eligible for selection for all ${\displaystyle n}$ draws. The usual estimator for the ${\displaystyle \mu }$ is the sample average

${\displaystyle {\overline {X}}={\frac {1}{n}}\sum _{i=1}^{n}X_{i}}$

which has an expected value equal to the true mean ${\displaystyle \mu }$ (so it is unbiased) and a mean squared error of

${\displaystyle \operatorname {MSE} \left({\overline {X}}\right)=\operatorname {E} \left[\left({\overline {X}}-\mu \right)^{2}\right]=\left({\frac {\sigma }{\sqrt {n}}}\right)^{2}={\frac {\sigma ^{2}}{n}}}$

where ${\displaystyle \sigma ^{2}}$ is the population variance.

For a Gaussian distribution, this is the best unbiased estimator (i.e., one with the lowest MSE among all unbiased estimators), but not, say, for a uniform distribution.

The usual estimator for the variance is the corrected sample variance:

${\displaystyle S_{n-1}^{2}={\frac {1}{n-1}}\sum _{i=1}^{n}\left(X_{i}-{\overline {X}}\right)^{2}={\frac {1}{n-1}}\left(\sum _{i=1}^{n}X_{i}^{2}-n{\overline {X}}^{2}\right).}$

This is unbiased (its expected value is ${\displaystyle \sigma ^{2}}$), hence also called the unbiased sample variance, and its MSE is[8]

${\displaystyle \operatorname {MSE} (S_{n-1}^{2})={\frac {1}{n}}\left(\mu _{4}-{\frac {n-3}{n-1}}\sigma ^{4}\right)={\frac {1}{n}}\left(\gamma _{2}+{\frac {2n}{n-1}}\right)\sigma ^{4},}$

where ${\displaystyle \mu _{4}}$ is the fourth central moment of the distribution or population, and ${\displaystyle \gamma _{2}=\mu _{4}/\sigma ^{4}-3}$ is the excess kurtosis.

However, one can use other estimators for ${\displaystyle \sigma ^{2}}$ which are proportional to ${\displaystyle S_{n-1}^{2}}$, and an appropriate choice can always give a lower mean squared error. If we define

${\displaystyle S_{a}^{2}={\frac {n-1}{a}}S_{n-1}^{2}={\frac {1}{a}}\sum _{i=1}^{n}\left(X_{i}-{\overline {X}}\,\right)^{2}}$

then we calculate:

${\displaystyle {\begin{aligned}\operatorname {MSE} (S_{a}^{2})&=\operatorname {E} \left[\left({\frac {n-1}{a}}S_{n-1}^{2}-\sigma ^{2}\right)^{2}\right]\\&=\operatorname {E} \left[{\frac {(n-1)^{2}}{a^{2}}}S_{n-1}^{4}-2\left({\frac {n-1}{a}}S_{n-1}^{2}\right)\sigma ^{2}+\sigma ^{4}\right]\\&={\frac {(n-1)^{2}}{a^{2}}}\operatorname {E} \left[S_{n-1}^{4}\right]-2\left({\frac {n-1}{a}}\right)\operatorname {E} \left[S_{n-1}^{2}\right]\sigma ^{2}+\sigma ^{4}\\&={\frac {(n-1)^{2}}{a^{2}}}\operatorname {E} \left[S_{n-1}^{4}\right]-2\left({\frac {n-1}{a}}\right)\sigma ^{4}+\sigma ^{4}&&\operatorname {E} \left[S_{n-1}^{2}\right]=\sigma ^{2}\\&={\frac {(n-1)^{2}}{a^{2}}}\left({\frac {\gamma _{2}}{n}}+{\frac {n+1}{n-1}}\right)\sigma ^{4}-2\left({\frac {n-1}{a}}\right)\sigma ^{4}+\sigma ^{4}&&\operatorname {E} \left[S_{n-1}^{4}\right]=\operatorname {MSE} (S_{n-1}^{2})+\sigma ^{4}\\&={\frac {n-1}{na^{2}}}\left((n-1)\gamma _{2}+n^{2}+n\right)\sigma ^{4}-2\left({\frac {n-1}{a}}\right)\sigma ^{4}+\sigma ^{4}\end{aligned}}}$

This is minimized when

${\displaystyle a={\frac {(n-1)\gamma _{2}+n^{2}+n}{n}}=n+1+{\frac {n-1}{n}}\gamma _{2}.}$

For a Gaussian distribution, where ${\displaystyle \gamma _{2}=0}$, this means that the MSE is minimized when dividing the sum by ${\displaystyle a=n+1}$. The minimum excess kurtosis is ${\displaystyle \gamma _{2}=-2}$,[lower-alpha 1] which is achieved by a Bernoulli distribution with p = 1/2 (a coin flip), and the MSE is minimized for ${\displaystyle a=n-1+{\tfrac {2}{n}}.}$ Hence regardless of the kurtosis, we get a "better" estimate (in the sense of having a lower MSE) by scaling down the unbiased estimator a little bit; this is a simple example of a shrinkage estimator: one "shrinks" the estimator towards zero (scales down the unbiased estimator).

Further, while the corrected sample variance is the best unbiased estimator (minimum mean squared error among unbiased estimators) of variance for Gaussian distributions, if the distribution is not Gaussian, then even among unbiased estimators, the best unbiased estimator of the variance may not be ${\displaystyle S_{n-1}^{2}.}$

The following table gives several estimators of the true parameters of the population, μ and σ², for the Gaussian case.[9]

True value	Estimator	Mean squared error
${\displaystyle \theta =\mu }$	${\displaystyle {\hat {\theta }}}$ = the unbiased estimator of the population mean, ${\displaystyle {\overline {X}}={\frac {1}{n}}\sum _{i=1}^{n}(X_{i})}$	${\displaystyle \operatorname {MSE} ({\overline {X}})=\operatorname {E} (({\overline {X}}-\mu )^{2})=\left({\frac {\sigma }{\sqrt {n}}}\right)^{2}}$
${\displaystyle \theta =\sigma ^{2}}$	${\displaystyle {\hat {\theta }}}$ = the unbiased estimator of the population variance, ${\displaystyle S_{n-1}^{2}={\frac {1}{n-1}}\sum _{i=1}^{n}\left(X_{i}-{\overline {X}}\,\right)^{2}}$	${\displaystyle \operatorname {MSE} (S_{n-1}^{2})=\operatorname {E} ((S_{n-1}^{2}-\sigma ^{2})^{2})={\frac {2}{n-1}}\sigma ^{4}}$
${\displaystyle \theta =\sigma ^{2}}$	${\displaystyle {\hat {\theta }}}$ = the biased estimator of the population variance, ${\displaystyle S_{n}^{2}={\frac {1}{n}}\sum _{i=1}^{n}\left(X_{i}-{\overline {X}}\,\right)^{2}}$	${\displaystyle \operatorname {MSE} (S_{n}^{2})=\operatorname {E} ((S_{n}^{2}-\sigma ^{2})^{2})={\frac {2n-1}{n^{2}}}\sigma ^{4}}$
${\displaystyle \theta =\sigma ^{2}}$	${\displaystyle {\hat {\theta }}}$ = the biased estimator of the population variance, ${\displaystyle S_{n+1}^{2}={\frac {1}{n+1}}\sum _{i=1}^{n}\left(X_{i}-{\overline {X}}\,\right)^{2}}$	${\displaystyle \operatorname {MSE} (S_{n+1}^{2})=\operatorname {E} ((S_{n+1}^{2}-\sigma ^{2})^{2})={\frac {2}{n+1}}\sigma ^{4}}$

The use of mean squared error without question has been criticized by the decision theorist James Berger. Mean squared error is the negative of the expected value of one specific utility function, the quadratic utility function, which may not be the appropriate utility function to use under a given set of circumstances. There are, however, some scenarios where mean squared error can serve as a good approximation to a loss function occurring naturally in an application.[10]

Like variance, mean squared error has the disadvantage of heavily weighting outliers.[11] This is a result of the squaring of each term, which effectively weights large errors more heavily than small ones. This property, undesirable in many applications, has led researchers to use alternatives such as the mean absolute error, or those based on the median.