eMixMargDen              package:bayesm              R Documentation

_C_o_m_p_u_t_e _M_a_r_g_i_n_a_l _D_e_n_s_i_t_i_e_s _o_f _A _N_o_r_m_a_l _M_i_x_t_u_r_e _A_v_e_r_a_g_e_d _o_v_e_r _M_C_M_C _D_r_a_w_s

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

     'eMixMargDen' assumes that a multivariate mixture of normals has
     been fitted via MCMC (using 'rnmixGibbs').  For each MCMC draw,
     the marginal densities for each component in the multivariate
     mixture are computed on a user-supplied grid and then averaged
     over draws.

_U_s_a_g_e:

     eMixMargDen(grid, probdraw, compdraw)

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

    grid: array of grid points, grid[,i] are ordinates for ith
          component 

probdraw: array - each row of which contains a draw of probabilities of
          mixture comp 

compdraw: list of lists of draws of mixture comp moments 

_D_e_t_a_i_l_s:

     length(compdraw) is number of MCMC draws. 
      compdraw[[i]] is a list draws of mu and inv Chol root for each of
     mixture components. 
      compdraw[[i]][[j]] is jth component.  compdraw[[i]][[j]]$mu is
     mean vector; compdraw[[i]][[j]]$rooti is the UL decomp of
     Sigma^{-1}.

_V_a_l_u_e:

     an array of the same dimension as grid with density values.

_W_a_r_n_i_n_g:

     This routine is a utility routine that does *not* check the input
     arguments for proper dimensions and type. To avoid errors, call
     with output from 'rnmixGibbs'.

_A_u_t_h_o_r(_s):

     Peter Rossi, Graduate School of Business, University of Chicago,
     Peter.Rossi@ChicagoGsb.edu.

_R_e_f_e_r_e_n_c_e_s:

     For further discussion, see _Bayesian Statistics and Marketing_ by
     Rossi, Allenby and McCulloch. 
      <URL:
     http://gsbwww.uchicago.edu/fac/peter.rossi/research/bsm.html>

_S_e_e _A_l_s_o:

     'rnmixGibbs'

