lh                 package:evdbayes                 R Documentation

_C_a_l_c_u_l_a_t_e _L_o_g-_l_i_k_e_l_i_h_o_o_d_s

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

     Calculate log-likelihoods for the gev, order statistics or point
     process models.

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

     pplik(par, data, thresh, noy, trend, exact = FALSE)
     gevlik(par, data, trend)
     oslik(par, data, trend) 

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

     par: If 'trend' is missing, should be a numeric vector of length
          three, containing the location, scale and shape parameters.
          If 'trend' is not missing, should be a numeric vector of
          length four, containing the location intercept, scale, shape
          and location trend parameters, in that order.

    data: For 'pplik' and 'gevlik'; a non-empty numeric vector
          containing the data at which the likelihood is evaluated,
          possibly containing missing values. For 'oslik'; a numeric
          matrix (see the user's guide).

  thresh: Threshold. Typically a single number or a vector of the same
          length as 'data'.

     noy: Number of years/periods of observations, excluding any
          missing values.

   trend: Trend vector (optional). If given, should be the same length
          as 'data' for 'pplik' and 'gevlik'. For 'oslik', should
          contain one value for each row of 'data'.

   exact: In general, the point process likelihood includes an
          approximation to an integral. If 'exact' is 'TRUE', every
          value in 'trend' and 'thresh' is used for the approximation.

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

     See the user's guide.

_N_o_t_e:

     These functions are essentially internal, and need not be called
     by the user. They are documented only because their arguments
     (excluding 'par') can be passed to 'posterior'.

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

     'posterior', 'prior.prob'

