close Warning: Can't synchronize with repository "(default)" (/var/svn/tolp does not appear to be a Subversion repository.). Look in the Trac log for more information.

Changes between Version 16 and Version 17 of OfficialTolArchiveNetworkBysPrior


Ignore:
Timestamp:
Dec 26, 2010, 11:07:40 AM (15 years ago)
Author:
Víctor de Buen Remiro
Comment:

--

Legend:

Unmodified
Added
Removed
Modified

  • OfficialTolArchiveNetworkBysPrior

    v16 v17  
    1717
    1818In order to be estimated with [wiki:OfficialTolArchiveNetworkNonLinGloOpt NonLinGloOpt]
    19 (max-likelihood) and [wiki:OfficialTolArchiveNetworkBysSampler  BysSampler ]
     19(max-likelihood) and [wiki:OfficialTolArchiveNetworkBysSampler BysSampler ]
    2020(Bayesian sampler), each prior must define methods to calculate the logarithm
    2121of the likelihood (except an additive constant), its gradient and its hessian,
    … …  
    198198For example we can define a log-normal prior without to define explicitly
    199199its log-likelihood, gradient and hessian.
     200
     201== Composed priors ==
     202If you have a set of priors you can express as just one bye means of
     203
     204 * adding the log-likelihood functions, the gradients and the hessians,
     205 * concat the set of constraining inequations
     206 * take the maximum of lower bounds
     207 * take the minimum of upper bounds