How do you test if an instrument is weak?

A. Determining whether the R-squared statistic for the IV model increases when the instrument is used.

B. Regressing x on z, performing an F test of the hypothesis that the coefficient on z is zero, and then calculating 1/F.

C. Regressing x on z and determining whether the slope coefficient on z exceeds 0.01.

D. Performing a t-test of the Levitt-Angrist statistic.