Hello, I would like to implement kalman filter when the measurement matrix is time varying. the model is as follows:Yt = Ht * Zt + Et Ht = [ 1 Mt] Zt = Zt-1 + Vt.can anyone tell me how to do this with KALCVF function in iml. My problem is that my Ht is time varying while in KALCVF I need Ht to be time invariant.Many thanks in advance.tarik

Can't help with your function, but I would think the measurement matrix always needs to be time-variant if only to allow for incomplete sets of observations. (i.e. "1"s may sometimes be "0"s).

Thanks for your reply McWulf!Is there any other functions to use in sas/iml to implement the kalman filter.I'd like to implement the CAPM with Time varying parameters. the model is as follows:Ri(t) = alpha_i(t) + beta_i(t)* Rm(t) + E(t)alpha_i(t) = alpha_i(t-1) + u(t)beta_i(t) = beta_i(t-1) + v(t)in a kalman filter representation the model is:Ri(t) = [ 1 Rm(t)] * |alpha_i(t)| + E(t) |beta_i(t) ||alpha_i(t)| = |alpha_i(t)| + |v(t)||beta_i(t) | |beta_i(t) | |u(t)|any help on how can I implement it in SAS/iml?Hope have clearly explained my model.