LN_hier_existence

Function that evaluates the existence conditions for moments of useful quantities in the original data scale
when a log-normal linear mixed model is estimated.

Bayesian inference under log-normality assumption must be performed very carefully. In fact, under the common priors for the variance, useful quantities in the original data scale (like mean and quantiles) do not have posterior moments that are finite (Fabrizi et al. 2012 <doi:10.1214/12-BA733>). This package allows to easily carry out a proper Bayesian inferential procedure by fixing a suitable distribution (the generalized inverse Gaussian) as prior for the variance. Functions to estimate several kind of means (unconditional, conditional and conditional under a mixed model) and quantiles (unconditional and conditional) are provided.

Aldo Gardini

BayesLN

Bayesian Inference for Log-Normal Data

Enrico Fabrizi

Carlo Trivisano

LN_hier_existence function

<dl><dt>X</dt>
<dd>Design matrix for fixed effects.</dd>
<dt>Z</dt>
<dd>Design matrix for random effects.</dd>
<dt>Xtilde</dt>
<dd>Covariate patterns used for the leverage computation.</dd>
<dt>order_moment</dt>
<dd>Order of the posterior moments required to be finite.</dd>
<dt>s</dt>
<dd>Number of variances of the random effects.</dd>
<dt>m</dt>
<dd>Vector of size <code>s</code> (if s&gt;1) that indicates the dimensions of the random effect vectors.</dd></dl>

Arguments

Numerical evaluation of the log-normal conditioned means posterior moments — LN_hier_existence

<dl>

<dt>X</dt>
<dd>Design matrix for fixed effects.</dd>


<dt>Z</dt>
<dd>Design matrix for random effects.</dd>


<dt>Xtilde</dt>
<dd>Covariate patterns used for the leverage computation.</dd>


<dt>order_moment</dt>
<dd>Order of the posterior moments required to be finite.</dd>


<dt>s</dt>
<dd>Number of variances of the random effects.</dd>


<dt>m</dt>
<dd>Vector of size <code>s</code> (if s&gt;1) that indicates the dimensions of the random effect vectors.</dd>

</dl>

LN_hier_existence: Numerical evaluation of the log-normal conditioned means posterior moments

Description

Usage

Value

Arguments

Details