Score (statistics)

In statistics, the score, score function, efficient score^[1] or informant^[2] plays an important role in several aspects of inference. For example:

in formulating a test statistic for a locally most powerful test;^[3]
in approximating the error in a maximum likelihood estimate;^[4]
in demonstrating the asymptotic sufficiency of a maximum likelihood estimate;^[4]
in the formulation of confidence intervals;^[5]
in demonstrations of the Cramér–Rao inequality.^[6]

The score function also plays an important role in computational statistics, as it can play a part in the computation of maximum likelihood estimates.

1 Definition
2 Properties
- 2.1 Mean
- 2.2 Variance
3 Example
4 Applications
- 4.1 Scoring algorithm
- 4.2 Score test
5 See also
6 Notes
7 References

Definition

The score or efficient score ^[1] is the gradient (the vector of partial derivatives), with respect to some parameter $\theta$ , of the logarithm (commonly the natural logarithm) of the likelihood function. If the observation is $X$ and its likelihood is $L(\theta;X)$ , then the score $V$ can be found through the chain rule:

$V = \frac{\partial}{\partial\theta} \log L(\theta;X) = \frac{1}{L(\theta;X)} \frac{\partial L(\theta;X)}{\partial\theta}.$

Thus the score $V$ indicates the sensitivity of $L(\theta;X)$ (its derivative normalized by its value). Note that $V$ is a function of $\theta$ and the observation $X$ , so that, in general, it is not a statistic. However in certain applications, such as the score test, the score is evaluated at a specific value of $\theta$ (such as a null-hypothesis value, or at the maximum likelihood estimate of $\theta$ ), in which case the result is a statistic.

Properties

Mean

Under some regularity conditions, the expected value of $V$ with respect to the observation $x$ , given $\theta$ , written $\mathbb{E}(V|\theta)$ , is zero. To see this rewrite the likelihood function $L(\theta; x) = f(x; \theta)$ as a probability density function,

$\mathbb{E}(V|\theta) =\int_{x=-\infty}^{%2B\infty} \frac{\frac{\partial f(x; \theta)}{\partial \theta}}{f(x; \theta)} f(x; \theta) dx = \int_{x=-\infty}^{%2B\infty} \frac{\partial f(x; \theta)}{\partial \theta} dx$

If certain differentiability conditions are met, the integral may be rewritten as

$\frac{\partial}{\partial\theta} \int_{x=-\infty}^{%2B\infty} f(x; \theta) \, dx = \frac{\partial}{\partial\theta}1 = 0.$

It is worth restating the above result in words: the expected value of the score is zero. Thus, if one were to repeatedly sample from some distribution, and repeatedly calculate the score, then the mean value of the scores would tend to zero as the number of repeat samples approached infinity.

Variance

Main article: Fisher information

The variance of the score is known as the Fisher information and is written $\mathcal{I}(\theta)$ . Because the expectation of the score is zero, this may be written as

$\mathcal{I}(\theta) = \mathbb{E} \left\{\left. \left[ \frac{\partial}{\partial\theta} \log L(\theta;X) \right]^2 \right|\theta\right\}.$

Note that the Fisher information, as defined above, is not a function of any particular observation, as the random variable $X$ has been averaged out. This concept of information is useful when comparing two methods of observation of some random process.

Example

Consider a Bernoulli process, with A successes and B failures; the probability of success is θ.

Then the likelihood L is

$L(\theta;A,B)=\frac{(A%2BB)!}{A!B!}\theta^A(1-\theta)^B,$

so the score V is

$V=\frac{1}{L}\frac{\partial L}{\partial\theta} = \frac{A}{\theta}-\frac{B}{1-\theta}.$

We can now verify that the expectation of the score is zero. Noting that the expectation of A is nθ and the expectation of B is n(1 − θ), we can see that the expectation of V is

$E(V) = \frac{n\theta}{\theta} - \frac{n(1-\theta)}{1-\theta} = n - n = 0.$

We can also check the variance of $V$ . We know that A + B = n (so B = n - A) and the variance of A is nθ(1 − θ) so the variance of V is

$\operatorname{var}(V)=\operatorname{var}\left(\frac{A}{\theta}-\frac{n-A}{1-\theta}\right) =\operatorname{var}\left(A\left(\frac{1}{\theta}%2B\frac{1}{1-\theta}\right)\right) =\left(\frac{1}{\theta}%2B\frac{1}{1-\theta}\right)^2\operatorname{var}(A) =\frac{n}{\theta(1-\theta)}.$

Applications

Scoring algorithm

Main article: Scoring algorithm

The scoring algorithm is an iterative method for numerically determining the maximum likelihood estimator.

Score test

Main article: Score test

Notes

^ ^a ^b Cox & Hinkley (1974), p 107
^ Chentsov, N.N. (2001), "Informant", in Hazewinkel, Michiel, Encyclopedia of Mathematics, Springer, ISBN 978-1556080104, http://www.encyclopediaofmath.org/index.php?title=i/i051030
^ Cox & Hinkley (1974), p 113
^ ^a ^b Cox & Hinkley (1974), p 295
^ Cox & Hinkley (1974), p 222-3
^ Cox & Hinkley (1974), p 254

References

Cox, D.R., Hinkley, D.V. (1974) Theoretical Statistics, Chapman & Hall. ISBN 0-412-12420-3
Schervish, Mark J. (1995). Theory of Statistics. New York: Springer. Section 2.3.1. ISBN 0387945466.