BaumWelch            package:HiddenMarkov            R Documentation

_E_s_t_i_m_a_t_e _P_a_r_a_m_e_t_e_r_s _U_s_i_n_g _B_a_u_m-_W_e_l_c_h _A_l_g_o_r_i_t_h_m

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

     Estimates the parameters of a hidden Markov model. The Baum-Welch
     algorithm (Baum et al, 1970) referred to in the HMM literature is
     a version of the EM algorithm (Dempster et al, 1977).

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

     BaumWelch(object, control, ...)
     ## S3 method for class 'dthmm':
     BaumWelch(object, control = bwcontrol(), ...)
     ## S3 method for class 'mmglm':
     BaumWelch(object, control = bwcontrol(), ...)
     ## S3 method for class 'mmpp':
     BaumWelch(object, control = bwcontrol(), ...)

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

  object: an object of class '"dthmm"', '"mmglm"', or '"mmpp"'.

 control: a list of control settings for the iterative process. These
          can be changed by using the function 'bwcontrol'.

     ...: other arguments.

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

     The initial parameter values used in the EM algorithm are those
     that are contained within the input object.

     The code for the methods '"dthmm"', '"mmglm"' and '"mmpp"' can be
     viewed by typing 'BaumWelch.dthmm', 'BaumWelch.mmglm' or
     'BaumWelch.mmpp', respectively, on the R command line.

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

     The output object (a 'list') with have the same class as the
     input, and will have the same components. The parameter values
     will be replaced by those estimated by this function. The object
     will also contain additional components. 

     An object of class '"dthmm"' will also contain 

       u: an n times m matrix containing estimates of the conditional
          expectations. See "Details" in 'Estep'.

       v: an n times m times m array containing estimates of the
          conditional expectations. See "Details" in 'Estep'.

      LL: value of log-likelihood at the end.

    iter: number of iterations performed.

    diff: difference between final and previous log-likelihood.

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

     Baum, L.E.; Petrie, T.; Soules, G. & Weiss, N. (1970). A
     maximization technique occurring in the statistical analysis of
     probabilistic functions of Markov chains. _Annals of Mathematical
     Statistics_ *41(1)*, 164-171.

     Dempster, A.P.; Laird, N.M. & Rubin, D.B. (1977). Maximum
     likelihood from incomplete data via the EM algorithm (with
     discussion). _J. Royal Statist. Society B_ *39(1)*, 1-38.

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

     'logLik', 'residuals', 'simulate', 'summary'

