selectSETAR              package:tsDyn              R Documentation

_A_u_t_o_m_a_t_i_c _s_e_l_e_c_t_i_o_n _o_f _S_E_T_A_R _h_y_p_e_r-_p_a_r_a_m_e_t_e_r_s

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

     Automatic selection of SETAR hyper-parameters

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

     selectSETAR(x, m, d=1, steps=d, thSteps=7, 
             mL = 1:m, mH = 1:m, 
             th=quantile(x, prob=seq(0.15, 0.85, length=thSteps) ), 
             thDelay=0:(m-1), criterion=c("pooled-AIC","AIC"))

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

       x: time series 

m, d, steps: embedding parameters. For their meanings, see help about
          'nlar' 

 thSteps: Number of steps along different values of threshold (if 'th'
          omitted) 

      th: Vector of threshold values 

   mL,mH: Vector of 'low' and 'high' regimes autoregressive orders

 thDelay: Vector of 'threshold delay' values

criterion: Model selection criterion  

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

     Routine for automatic selection of SETAR models hyper parameters.

     An exhaustive search over all possible combinations of values of
     specified hyper-parameters is performed.

     Embedding parameters 'm,d,steps' are kept fixed.

     Possible criteria are the usual AIC and a pooled AIC formula:
     AIC(low regime model) + AIC(high regime model). The default
     criterion is the pooled AIC formula.

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

     A data-frame, with columns giving hyper-parameter values and the
     computed AIC for each row (only the best 10s are returned)

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

     Antonio, Fabio Di Narzo

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

     'selectLSTAR', 'selectNNET'

_E_x_a_m_p_l_e_s:

     llynx <- log10(lynx)
     selectSETAR(llynx, m=2)
     #Suggested model is the following:
     setar(llynx, m=2, thDelay=1, th=3.4)

