pgam.psi2par

Put hyperparameters into unconstrained form for optimization.

internal

This work is an extension of the state space model for Poisson count data, Poisson-Gamma model, towards a semiparametric specification. Just like the generalized additive models (GAM), cubic splines are used for covariate smoothing. The semiparametric models are fitted by an iterative process that combines maximization of likelihood and backfitting algorithm.

Washington Junger

pgam

Poisson-Gamma Additive Models

pgam.psi2par function

<dl> <dt>w</dt>
<dd>discount factor of the Poisson-Gamma model</dd> <dt>beta</dt>
<dd>explanatory variables coefficients</dd> <dt>fperiod</dt>
<dd>vector containing as many seasonal factors as there are in model formula</dd></dl>

Arguments

Washington Leite Junger <a href="/link/wjunger%40ims.uerj.br?package=pgam&version=0.4.17" data-mini-rdoc="pgam::wjunger@ims.uerj.br">wjunger@ims.uerj.br</a> and Antonio Ponce de Leon <a href="/link/ponce%40ims.uerj.br?package=pgam&version=0.4.17" data-mini-rdoc="pgam::ponce@ims.uerj.br">ponce@ims.uerj.br</a>

Author

Utility function — pgam.psi2par

<dl>

 <dt>w</dt>
<dd>discount factor of the Poisson-Gamma model</dd>

 <dt>beta</dt>
<dd>explanatory variables coefficients</dd>

 <dt>fperiod</dt>
<dd>vector containing as many seasonal factors as there are in model formula</dd>

</dl>

Washington Leite Junger <a href='mailto:wjunger@ims.uerj.br'>wjunger@ims.uerj.br</a> and Antonio Ponce de Leon <a href='mailto:ponce@ims.uerj.br'>ponce@ims.uerj.br</a>

pgam.psi2par: Utility function

Description

Usage

Value

Arguments

Author

See Also