On a consistent rank estimate in a linear structural model

The structural linear model is considered that is an errors-in- -variables model where the unobserved variables are i.i.d. In this model we can find linear transformations depending on the parameter, such that the transformed observations using the true parameter are uncorrelated. Then a parameter estimator is defined as a zero point of a consistent correlation estimator. A rank estimation is proposed as a zero point of Kendall’s correlation measure and its consistency is shown. While the Pearson estimate of the covariance delivers the total least squares estimate.