updated documentation

DESCRIPTION

 Package: bayesmeta
 Type: Package
 Title: Bayesian Random-Effects Meta-Analysis and Meta-Regression
-Version: 2.75
-Date: 2021-02-24
+Version: 2.65
+Date: 2021-02-25
 Authors@R: c(person(given="Christian", family="Roever", role=c("aut","cre"), 
                     email="christian.roever@med.uni-goettingen.de",
                     comment=c(ORCID="0000-0002-6911-698X")),

man/bayesmeta-package.Rd

@@ -16,8 +16,8 @@
   \tabular{ll}{
     Package: \tab bayesmeta\cr
     Type:    \tab Package\cr
-    Version: \tab 2.75\cr
-    Date:    \tab 2021-02-24\cr
+    Version: \tab 2.65\cr
+    Date:    \tab 2021-02-25\cr
     License: \tab GPL (>=2)
   }
   The main functionality is provided by the \code{\link{bayesmeta}()}

man/bmr.Rd

@@ -135,12 +135,16 @@
   d}) \emph{regressor matrix}, and \eqn{\Sigma} is a (\eqn{k \times k}{k x
   k}) diagonal covariance matrix containing the
   \eqn{\sigma_i^2}{sigma[i]^2} values, while
-  \eqn{I} is the (\eqn{k \times k}{k x
-  k}) identity matrix.
+  \eqn{I} is the (\eqn{k \times k}{k x k}) identity matrix. The
+  regressor matrix \eqn{X} plays a crucial role here, as the
+  \sQuote{\code{X}} argument (with rows corresponding to studies, and
+  columns corresponding to covariables) is required to specify the exact
+  regression setup.
 
   Meta-regression allows the consideration of (study-level) covariables
   in a meta-analysis. Quite often, these may also be indicator variables
   (\sQuote{zero/one} variables) simply identifying subgroups of studies.
+  See also the examples shown below.
 
 \subsection{Connection to the simple random-effects model}{
   The meta-regression model is a generalisation of the \sQuote{simple}
@@ -177,6 +181,17 @@
   accuracy of the computations is determined by the \sQuote{\code{delta}}
   and \sQuote{\code{epsilon}} arguments (Roever and Friede,
   2017).
+
+  A slight difference between the \code{\link{bayesmeta}()} and
+  \code{bmr()} implementations exists in the determination of the grid
+  approximation within the \acronym{DIRECT} algorithm. While
+  \code{bmr()} considers divergences w.r.t. the conditional posterior
+  distributions \eqn{p(\beta|\tau)}, \code{bayesmeta()} in addition
+  considers divergences w.r.t. the shrinkage estimates, which in general
+  leads to a denser binning (as one can see from the numbers of bins
+  required; see the example below). A denser binning within the
+  \code{bmr()} function may be achieved by reducing the
+  \sQuote{\code{delta}} argument.
   }
 }
 \value{