King and Watson (KW) show that testing long-run neutrality within a SVAR framework requires the data to be / (1). They characterize long-run neutrality of money using the SMA representation for yt = (y, Am.) written as output: Aye = My + 0 yy ( L ) Eyt + 0ym (L) Emt money : Am, = Hm + 0my(L)Eyt + 0mm(L)Emt where Eye represents exogenous shocks to output that are uncorrelated with exogenous shocks to nominal money Emt. If an unexpected and exogenous permanent change in the level of money leads to a permanent change in the level of output then money is not long-run neutral towards output. With the data in logs, the long-run elasticity of output with respect to permanent changes in money is Yum = ym (1) mm (I) Money is neutral in the long-run when Gym (1) = 0 or ym = 0 Assume that the SMA representation is derived from the simple SVAR(1) model Aye = Cy + d ym Am , + 0 1 , yy yt_ 1 + 1, ym my_1 + Eyt Am . = Cm + 1 my y+ + 2 1, my yt_ 1 + 1,mmm,_1 + Emt which has the form BAy, = c+ryt 1tet B = 1 my r = a 1, yy a 1,ym a 1 . my a 1 , mm Eyt 0 02 0 iid N Emt Assume that the long-run elasticity of money wrt output e my (1) Ymy Byy ( 1) is known. For example, one might assume Ymy = 1 which is consistent with long-run price stability under the assumption that velocity is stable. (a) Show how the SVAR model parameters may be consistently estimated when my is known. (b) Given the estimates of the SVAR model parameters when my is known, show how Yum may be estimated. (c) Briefly discuss how you would compute a standard error for the estimate of ym' You do not have to give explicit details of this calculation