Alternative errors-in-variables models and their applications in finance research

Abstract

tSpecification error and measurement error are two major issues in finance research. The main purposeof this paper is (i) to review and extend existing errors-in-variables (EIV) estimation methods, includingclassical method, grouping method, instrumental variable method, mathematical programming method,maximum likelihood method, LISREL method, and the Bayesian approach; (ii) to investigate how EIVestimation methods have been used to finance related studies, such as cost of capital, capital structure,investment equation, and test capital asset pricing models; and (iii) to give a more detailed explanationof the methods used by Almeida et al. (2010).