sample_alpha_cowles

One Metropolis-Hastings sweep on <code>alpha</code> with Z integrated out
of the conditional. The proposal is a symmetric random walk in
<code>delta = log(diff(alpha))</code> space; the acceptance ratio uses
the marginal ordinal-probit likelihood. Mixing of <code>alpha</code>
under this update is dramatically faster than the data-induced
Gibbs convention (Cowles 1996 reports ESS gains of an order of
magnitude on standard ordinal-probit benchmarks).

internal

Additive and multiplicative effects models for both cross-sectional and longitudinal network analysis. The package provides two main functions: ame() for cross-sectional networks and lame() for longitudinal networks. It supports square and rectangular network structures. Key features include: (1) Cross-sectional network analysis via ame() with support for binary, continuous, ordinal, and count data; (2) Longitudinal network analysis via lame() with additive sender/receiver and multiplicative latent-factor effects that can evolve over time through AR(1) processes (Sewell and Chen (2015) <doi:10.1080/01621459.2014.988214>; Durante and Dunson (2014) <doi:10.1093/biomet/asu040>); (3) Handling of changing actor compositions across time periods in longitudinal models; (4) Performance improvements through C++ implementations via 'Rcpp' and 'RcppArmadillo'.

Shahryar Minhas

lame

Longitudinal Additive and Multiplicative Effects Models for
Networks

Cassy Dorff

Tosin Salau

sample_alpha_cowles function

<dl><dt>alpha</dt>
<dd>numeric, current cutpoints with <code>alpha[1] = 0</code>,
length <code>K-1</code>.</dd>
<dt>Y_int</dt>
<dd>integer matrix (or array) of ordinal categories coded
1..K, with <code>NA</code> for missing cells.</dd>
<dt>EZ</dt>
<dd>linear predictor at the dyad level, same shape as
<code>Y_int</code>.</dd>
<dt>tau_prop</dt>
<dd>numeric, RW proposal SD in delta space (will be
adapted in burn-in by the caller).</dd>
<dt>symmetric</dt>
<dd>logical, whether the network is symmetric (restricts
the likelihood to upper-triangle cells so each dyad is counted once;
variance 1, no precision rescaling).</dd></dl>

Arguments

Cassy Dorff, Shahryar Minhas, Tosin Salau

Author

Cowles MH update for explicit ordinal cutpoints (Z-marginalised) — sample_alpha_cowles

<dl>

<dt>alpha</dt>
<dd>numeric, current cutpoints with <code>alpha[1] = 0</code>,
length <code>K-1</code>.</dd>


<dt>Y_int</dt>
<dd>integer matrix (or array) of ordinal categories coded
1..K, with <code>NA</code> for missing cells.</dd>


<dt>EZ</dt>
<dd>linear predictor at the dyad level, same shape as
<code>Y_int</code>.</dd>


<dt>tau_prop</dt>
<dd>numeric, RW proposal SD in delta space (will be
adapted in burn-in by the caller).</dd>


<dt>symmetric</dt>
<dd>logical, whether the network is symmetric (restricts
the likelihood to upper-triangle cells so each dyad is counted once;
variance 1, no precision rescaling).</dd>

</dl>

sample_alpha_cowles: Cowles MH update for explicit ordinal cutpoints (Z-marginalised)

Description

Usage

Value

Arguments

Author