logLik-AIC-methods           package:ghyp           R Documentation

_E_x_t_r_a_c_t _L_o_g-_L_i_k_e_l_i_h_o_o_d _a_n_d _A_k_a_i_k_e'_s _I_n_f_o_r_m_a_t_i_o_n _C_r_i_t_e_r_i_o_n

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

     The functions 'logLik' and 'AIC'  extract the Log-Likelihood and
     the Akaike's Information Criterion from fitted generalized
     hyperbolic distribution objects. The Akaike information criterion
     is calculated according to the formula -2*log-likelihood + k*npar,
     where npar represents the number of parameters in the fitted
     model, and k = 2 for the usual AIC.

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

     ## S4 method for signature 'mle.ghyp':
     logLik(object, ...)

     ## S4 method for signature 'mle.ghyp':
     AIC(object, ..., k = 2)

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

  object: An object of class 'mle.ghyp'.

       k: The "penalty" per parameter to be used; the default k = 2 is
          the classical AIC.

     ...: An arbitrary number of objects of class 'mle.ghyp'.

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

     Either the Log-Likelihood or the Akaike's Information Criterion.

_N_o_t_e:

     The Log-Likelihood as well as the Akaike's Information Criterion
     can be obtained from the function 'ghyp.fit.info'. However, the
     benefit of 'logLik' and 'AIC' is that these functions allow a call
     with an arbitrary number of objects and are better known because
     they are generic.

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

     David Lthi

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

     'fit.ghypuv', 'fit.ghypmv', 'lik.ratio.test',  'ghyp.fit.info',
     'mle.ghyp-class'

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

       data(smi.stocks)
       
       ## Multivariate fit
       fit.mv <- fit.hypmv(smi.stocks, nit = 10)
       AIC(fit.mv)
       logLik(fit.mv)
       
       ## Univariate fit
       fit.uv <- fit.tuv(smi.stocks[, "CS"], control = list(maxit = 10))
       AIC(fit.uv)
       logLik(fit.uv) 

