Score test


In statistics, the score test assesses constraints on statistical parameters based on the gradient of the likelihood function—known as the score—evaluated at the hypothesized parameter value under the null hypothesis. Intuitively, if the restricted estimator is near the maximum of the likelihood function, the score should not differ from zero by more than sampling error. While the finite sample distributions of score tests are generally unknown, it has an asymptotic χ2-distribution under the null hypothesis as first proved by C. R. Rao in 1948, a fact that can be used to determine statistical significance.
Since function maximization subject to equality constraints is most conveniently done using a Lagrangean expression of the problem, the score test can be equivalently understood as a test of the magnitude of the Lagrange multipliers associated with the constraints where, again, if the constraints are non-binding at the maximum likelihood, the vector of Lagrange multipliers should not differ from zero by more than sampling error. The equivalence of these two approaches was first shown by S. D. Silvey in 1959, which led to the name Lagrange multiplier test that has become more commonly used, particularly in econometrics, since Breusch and Pagan's much-cited 1980 paper.
The main advantage of the score test over the Wald test and likelihood-ratio test is that the score test only requires the computation of the restricted estimator. This makes testing feasible when the unconstrained maximum likelihood estimate is a boundary point in the parameter space. Further, because the score test only requires the estimation of the likelihood function under the null hypothesis, it is less specific than the other two tests about the precise nature of the alternative hypothesis.

Single parameter test

The statistic

Let be the likelihood function which depends on a univariate parameter and let be the data. The score is defined as
The Fisher information is
The statistic to test is
which has an asymptotic distribution of, when is true. While asymptotically identical, calculating the LM statistic using the outer-gradient-product estimator of the Fisher information matrix can lead to bias in small samples.

Note on notation

Note that some texts use an alternative notation, in which the statistic is tested against a normal distribution. This approach is equivalent and gives identical results.

As most powerful test for small deviations

where is the likelihood function, is the value of the parameter of interest under the null hypothesis, and is a constant set depending on the size of the test desired.
The score test is the most powerful test for small deviations from. To see this, consider testing versus. By the Neyman–Pearson lemma, the most powerful test has the form
Taking the log of both sides yields
The score test follows making the substitution
and identifying the above with.

Relationship with other hypothesis tests

If the null hypothesis is true, the likelihood ratio test, the Wald test, and the Score test are asymptotically equivalent tests of hypotheses. When testing nested models, the statistics for each test then converge to a Chi-squared distribution with degrees of freedom equal to the difference in degrees of freedom in the two models. If the null hypothesis is not true, however, the statistics converge to a noncentral chi-squared distribution with possibly different noncentrality parameters.

Multiple parameters

A more general score test can be derived when there is more than one parameter. Suppose that is the maximum likelihood estimate of under the null hypothesis while and are respectively, the score and the Fisher information matrices under the alternative hypothesis. Then
asymptotically under, where is the number of constraints imposed by the null hypothesis and
and
This can be used to test.

Special cases

In many situations, the score statistic reduces to another commonly used statistic.
In linear regression, the Lagrange multiplier test can be expressed as a function of the F-test.
When the data follows a normal distribution, the score statistic is the same as the t statistic.
When the data consists of binary observations, the score statistic is the same as the chi-squared statistic in the Pearson's chi-squared test.
When the data consists of failure time data in two groups, the score statistic for the Cox partial likelihood is the same as the log-rank statistic in the log-rank test. Hence the log-rank test for difference in survival between two groups is most powerful when the proportional hazards assumption holds.