Wald test

The Wald test is a parametric statistical test named after the statistician Abraham Wald. Whenever a relationship within or between data items can be expressed as a statistical model with parameters to be estimated from a sample, the Wald test can be used to test the true value of the parameter based on the sample estimate.

Suppose a social scientist, who has data on social class and shoe size, wonders whether social class is associated with shoe size. Say $\theta$ is the average increase in shoe size for upper-class people compared to middle-class people: then the Wald test can be used to test whether $\theta$ is 0 (in which case social class has no association with shoe size) or non-zero (shoe size varies between social classes). Here, $\theta$ , the hypothetical difference in shoe sizes between upper and middle-class people in the whole population, is a parameter. An estimate of $\theta$ might be the difference in shoe size between upper and middle-class people in the sample. In the Wald test, the social scientist uses the estimate and an estimate of variability (see below) to draw conclusions about the unobserved true $\theta$ . Or, for a medical example, suppose smoking multiplies the risk of lung cancer by some number R: then the Wald test can be used to test whether R = 1 (i.e. there is no effect of smoking) or is greater (or less) than 1 (i.e. smoking alters risk).

A Wald test can be used in a great variety of different models including models for dichotomous variables and models for continuous variables.^[1]

Mathematical details

Under the Wald statistical test, the maximum likelihood estimate ${\hat {\theta }}$ of the parameter(s) of interest $\theta$ is compared with the proposed value $\theta _{0}$ , with the assumption that the difference between the two will be approximately normally distributed. Typically the square of the difference is compared to a chi-squared distribution.

Test on a single parameter

In the univariate case, the Wald statistic is

\frac{ ( \widehat{ \theta}-\theta_0 )^2 }{\operatorname{var}(\hat \theta )}

which is compared against a chi-squared distribution.

Alternatively, the difference can be compared to a normal distribution. In this case the test statistic is

\frac{\widehat{\theta}-\theta_0}{\operatorname{se}(\hat\theta)}

where $\operatorname{se}(\widehat\theta)$ is the standard error of the maximum likelihood estimate (MLE). A reasonable estimate of the standard error for the MLE can be given by $\frac{1}{\sqrt{I_n(MLE)}}$ , where $I_n$ is the Fisher information of the parameter.

Test(s) on multiple parameters

The Wald test can be used to test a single hypothesis on multiple parameters, as well as to test jointly multiple hypotheses on single/multiple parameters. Let ${\hat {\theta }}_{n}$ be our sample estimator of P parameters (i.e., ${\hat {\theta }}_{n}$ is a P $\times$ 1 vector), which is supposed to follow asymptotically a normal distribution with covariance matrix V, ${\sqrt {n}}({\hat {\theta }}_{n}-\theta ){\xrightarrow {{\mathcal {D}}}}N(0,V)$ . The test of Q hypotheses on the P parameters is expressed with a Q $\times$ P matrix R:

H_{0}:R\theta =r

H_{1}:R\theta \neq r

The test statistic is:

(R{\hat {\theta }}_{n}-r)^{'}[R({\hat {V}}_{n}/n)R^{'}]^{-1}(R{\hat {\theta }}_{n}-r)\quad {\xrightarrow {\mathcal {D}}}\quad \chi _{Q}^{2}

where ${\hat {V}}_{n}$ is an estimator of the covariance matrix.^[2]

Proof

Suppose ${\sqrt {n}}({\hat {\theta }}_{n}-\theta ){\xrightarrow {{\mathcal {D}}}}N(0,V)$ . Then, by Slutsky's theorem and by the properties of the normal distribution, multiplying by R has distribution:

R{\sqrt {n}}({\hat {\theta }}_{n}-\theta )={\sqrt {n}}(R{\hat {\theta }}_{n}-r){\xrightarrow {{\mathcal {D}}}}N(0,RVR^{{'}})

Recalling that a quadratic form of normal distribution has a Chi-squared distribution:

{\sqrt {n}}(R{\hat {\theta }}_{n}-r)^{'}[RVR^{'}]^{-1}{\sqrt {n}}(R{\hat {\theta }}_{n}-r){\xrightarrow {\mathcal {D}}}\chi _{Q}^{2}

Rearranging n finally gives:

(R{\hat {\theta }}_{n}-r)^{'}[R(V/n)R^{'}]^{-1}(R{\hat {\theta }}_{n}-r)\quad {\xrightarrow {\mathcal {D}}}\quad \chi _{Q}^{2}

What if the covariance matrix is not known a-priori and needs to be estimated from the data? If we have a consistent estimator ${\hat {V}}_{n}\sim \mathrm {X} _{n-P}^{2}$ of $V$ , then by the independence of the covariance estimator and equation above, we have:

(R{\hat {\theta }}_{n}-r)^{'}[R({\hat {V}}_{n}/n)R^{'}]^{-1}(R{\hat {\theta }}_{n}-r)\quad {\xrightarrow {\mathcal {D}}}\quad F(Q,n-P)

Nonlinear hypothesis

In the standard form, the Wald test is used to test linear hypotheses, that can be represented by a single matrix R. If one wishes to test a non-linear hypothesis of the form:

H_{0}:c(\theta )=0

H_{1}:c(\theta )\neq 0

The test statistic becomes:

c\left({\hat {\theta }}_{n}\right)'\left[c'\left({\hat {\theta }}_{n}\right)\left({\hat {V}}_{n}/n\right)c'\left({\hat {\theta }}_{n}\right)'\right]^{-1}c\left({\hat {\theta }}_{n}\right)\quad {\xrightarrow {\mathcal {D}}}\quad \chi _{Q}^{2}

where $c'({\hat {\theta }}_{n})$ is the derivative of c evaluated at the sample estimator. This result is obtained using the delta method, which uses a first order approximation of the variance.

Non-invariance to re-parameterisations

The fact that one uses an approximation of the variance has the drawback that the Wald statistic is not-invariant to a non-linear transformation/reparametrisation of the hypothesis: it can give different answers to the same question, depending on how the question is phrased.^[3] For example, asking whether R = 1 is the same as asking whether log R = 0; but the Wald statistic for R = 1 is not the same as the Wald statistic for log R = 0 (because there is in general no neat relationship between the standard errors of R and log R, so it needs to be approximated).

Alternatives to the Wald test

There exist several alternatives to the Wald test, namely the likelihood-ratio test and the Lagrange multiplier test (also known as the score test). Robert F. Engle showed that these three tests, the Wald test, the likelihood-ratio test and the Lagrange multiplier test are asymptotically equivalent.^[4] Although they are asymptotically equivalent, in finite samples, they could disagree enough to lead to different conclusions.

There are several reasons to prefer the likelihood ratio test or the Lagrange multiplier to the Wald test:^[5]^[6]^[7]

Non-invariance: As argued above, the Wald test is not invariant to a reparametrization, while the Likelihood ratio tests will give exactly the same answer whether we work with R, log R or any other monotonic transformation of R.
The other reason is that the Wald test uses two approximations (that we know the standard error, and that the distribution is chi-squared), whereas the likelihood ratio test uses one approximation (that the distribution is chi-squared).
The Wald test requires an estimate under the alternative hypothesis, corresponding to the "full" model. In some cases, the model is simpler under the zero hypothesis, so that one might prefer to use the score test (also called Lagrange Multiplier test), which has the advantage that it can be formulated in situations where the variability is difficult to estimate; e.g. the Cochran–Mantel–Haenzel test is a score test.^[8]

References

↑ Harrell, Frank E., Jr. (2001). "Sections 9.2, 10.5". Regression modeling strategies. New York: Springer-Verlag. ISBN 0387952322.
↑ Harrell, Frank E., Jr. (2001). "Section 9.3.1". Regression modeling strategies. New York: Springer-Verlag. ISBN 0387952322.
↑ Fears, Thomas R.; Benichou, Jacques; Gail, Mitchell H. (1996). "A reminder of the fallibility of the Wald statistic". The American Statistician. 50 (3): 226–227. doi:10.1080/00031305.1996.10474384.
↑ Engle, Robert F. (1983). "Wald, Likelihood Ratio, and Lagrange Multiplier Tests in Econometrics". In Intriligator, M. D.; Griliches, Z. Handbook of Econometrics. II. Elsevier. pp. 796–801. ISBN 978-0-444-86185-6.
↑ Harrell, Frank E., Jr. (2001). "Section 9.3.3". Regression modeling strategies. New York: Springer-Verlag. ISBN 0387952322.
↑ Collett, David (1994). Modelling Survival Data in Medical Research. London: Chapman & Hall. ISBN 0412448807.
↑ Pawitan, Yudi (2001). In All Likelihood. New York: Oxford University Press. ISBN 0198507658.
↑ Agresti, Alan (2002). Categorical Data Analysis (2nd ed.). Wiley. p. 232. ISBN 0471360937.

External links

This article is issued from Wikipedia. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.

[1] Harrell, Frank E., Jr. (2001). "Sections 9.2, 10.5". Regression modeling strategies. New York: Springer-Verlag. ISBN 0387952322.

[2] Harrell, Frank E., Jr. (2001). "Section 9.3.1". Regression modeling strategies. New York: Springer-Verlag. ISBN 0387952322.

[3] Fears, Thomas R.; Benichou, Jacques; Gail, Mitchell H. (1996). "A reminder of the fallibility of the Wald statistic". The American Statistician. 50 (3): 226–227. doi:10.1080/00031305.1996.10474384.

[4] Engle, Robert F. (1983). "Wald, Likelihood Ratio, and Lagrange Multiplier Tests in Econometrics". In Intriligator, M. D.; Griliches, Z. Handbook of Econometrics. II. Elsevier. pp. 796–801. ISBN 978-0-444-86185-6.

[5] Harrell, Frank E., Jr. (2001). "Section 9.3.3". Regression modeling strategies. New York: Springer-Verlag. ISBN 0387952322.

[6] Collett, David (1994). Modelling Survival Data in Medical Research. London: Chapman & Hall. ISBN 0412448807.

[7] Pawitan, Yudi (2001). In All Likelihood. New York: Oxford University Press. ISBN 0198507658.

[8] Agresti, Alan (2002). Categorical Data Analysis (2nd ed.). Wiley. p. 232. ISBN 0471360937.