This paper studies the properties of t-ratios associated with the limited information maximum likelihood (LIML) estimators in a structural form estimation when the number of instrumental variables is large. Asymptotic expansions are made of the distributions of a large K t-ratio statistic under large-Kn asymptotics. A modified t-ratio statistic is proposed from the asymptotic expansion. The power of the large K t-ratio test dominates the AR test, the K-test by Kleibergen (2002), and the conditional LR test by Moreira (2003); and the difference can be substantial when the instruments are weak.