Testing for the effects of omitted power transformations

We use the quasi-likelihood ratio statistic to test the hypothesis that a power transformation is ineffective. The null is not standard because a parameter is unidentified, and we can also let the power coefficient be zero for the null.

► To test for neglected nonlinearity, the QLR test is examined. ► The null behavior is shown to be approximated by a quadratic expansion. ► It is different from Cho et al. (2011), as a quartic expansion is avoided.