A0393
Title: On the instrumental variable estimation with many weak and invalid instruments
Authors: Qingliang Fan - The Chinese University of Hong Kong (Hong Kong) [presenting]
Abstract: The fundamental issue of identification in linear instrumental variable (IV) models with unknown IV validity is discussed. The popular majority and plurality rules are revisited, and the identification conditions, in general, are discussed. With the assumption of the sparsest rule, which is equivalent to the plurality rule but becomes operational in computation algorithms, the advantages of non-convex penalized approaches over other IV estimators based on two-step selections are investigated and proved in terms of selection consistency and accommodation for individually weak IVs. Furthermore, a surrogate sparsest penalty is proposed that aligns with the identification condition and provides an oracle sparse structure simultaneously. Desirable theoretical properties are derived for the proposed estimator with weaker IV strength conditions compared to the previous literature. Finite sample properties are demonstrated using simulations, and the selection and estimation method is applied to an empirical study concerning the effect of trade on economic growth.
