Simple search

The simple search algorithm is essentially an evaluation of a large number of randomly generated vectors of starting values. Each vector is evaluated at the starting values and sorted in descending order. The best fitting vectors of starting values are returned.

search_simple(
  ll,
  log_lik,
  param_free,
  n_candidates,
  n_return,
  multiplier,
  workers
)

Arguments

ll

This is the 'raw' log-likelihood function passed to the estimation routine. It is important that the user takes into account whether the optimization routine is a minimizer (e.g. 'ucminf') or a maximizer (e.g. 'maxlik').

log_lik

A log-likelihood expression prepared by prepare_log_lik

param_free

A list of freely estimated parameters

n_candidates

An integer giving the number of candidates to evaluate. Default is 100.

n_return

An integer giving the number of parameter vectors to return. The default is 10

multiplier

A double indicating a multiplier for the 'simple' search algorithm. The default is 1.

workers

A list of workers

Value

A matrix of starting values (free parameters only)