A particular test for structural change; an econometric test to determine whether the coefficients in a regression model are the same in separate subsamples. In reference to a paper of G.C. Chow (1960), "the standard F test for the equality of two sets of coefficients in linear regression models" is called a Chow test. See derivation and explanation in Davidson and MacKinnon, p. 375-376. More info in Greene, 2nd edition, p 211-2.

Homoskedasticity of errors is assumed although this can be dubious since we are open to the possibility that the parameter vector (b) has changed.
RSSR = the sum of squared residuals from a linear regression in which b₁ and b₂ are assumed to be the same
SSR₁ = the sum of squared residuals from a linear regression of sample 1
SSR₂ = the sum of squared residuals from a linear regression of sample 2
b has dimension k, and there are n observations in total
Then the F statistic is:
((RSSR-SSR₁-SSR₂)/k ) / ((SSR₁+SSR₂)/(n-2k).
That test statistic is the Chow test.