

corrarma(timeslab)                           R Documentation

_C_a_l_c_u_l_a_t_e _A_R_M_A _P_a_r_a_m_e_t_e_r_s _f_r_o_m _A_u_t_o_c_o_r_r_e_l_a_t_i_o_n_s

_D_e_s_c_r_i_p_t_i_o_n_:

     Calculate ARMA Parameters from Autocorrelations

_U_s_a_g_e_:

     corrarma(rho,r0,p,q,maxit=100,del=1.e-5)

_A_r_g_u_m_e_n_t_s_:

     rho: Array of length ${t{p}}+{t{q}}$ containing the
          autocorrelations of the process.

      r0: Real scalar containing the variance of the process
          $(>0)$.

       p: Integer containing AR order $p(>0)$.

       q: Integer containing MA order $q(>0)$.

   maxit: Integer containing the maximum number of itera-
          tions to allow in Wilson's algorithm.

     del: Real scalar containing convergence criterion
          $(>0)$.

_V_a_l_u_e_:

   alpha: Array of length {`p'} containing AR coefficients.

    beta: Array of length {`q'} containing MA coefficients.

    rvar: Real scalar containing the error variance
          $sigma^2$.

     ier: Integer variable containing an error/convergence
          indicator.  The following values are possible:

        : 0 ~~ {`CORRARMA'} successfully found the ARMA
          parameters.

        : 1 ~~ A singular matrix was encountered trying to
          find AR parameters.

        : 2 ~~ Wilson's algorithm for finding the MA parame-
          ters didn't converge.

