Diagnostics for IV Regressions

The use of residuals from the structural equations in a simultaneous-equations model can lead to misleading measures of association and to invalid diagnostic statistics for heteroscedasticity and functional form misspecifications. The issue of appropriate measures of goodness-of-fit for IV regression is addressed in Pesaran and Smith (1994). This paper considers the problem of appropriate construction of diagnostics for IV regressions, and proposes simple tests for functional form misspecifications and heteroscedasticity.