posterior_metrics

A fitted model object returned by <code><a rd-options="" href="/link/epim?package=epidemia&version=1.0.0" data-mini-rdoc="epidemia::epim">epim</a></code>.
See <code><a rd-options="" href="/link/epimodel-objects?package=epidemia&version=1.0.0" data-mini-rdoc="epidemia::epimodel-objects">epimodel-objects</a></code>.

object

A string specifying the name of the observations to plot. This should match one
of the names of the response variables in the <code>obs</code> argument used int the call to <code><a rd-options="" href="/link/epim?package=epidemia&version=1.0.0" data-mini-rdoc="epidemia::epim">epim</a></code>.

type

If provided, the original <code>data</code> used
in <code>object</code> is overridden. Useful for forecasting

newdata

Either <code>NULL</code> or a character vector specifying the groups
to plot for. Default is <code>NULL</code>, which plots all modeled groups.

groups

A string or character vector specifying the plotted
forecast error metrics. One of <code>NULL</code>, <code>"crps"</code>,
<code>"mean_abs_error"</code>

metrics

Calculate daily error using one of three metrics, and also return coverage
of credible intervals. Uses continuous ranked probability
score (CRPS), mean absolute error and median absolute error.

Flexibly specify and fit Bayesian statistical models for epidemics. 'epidemia' leverages Rs formula interface so
that users can parameterize reproduction numbers and ascertainment rates in terms of predictors. Infections are propagated over
time using self-exciting point processes. Multiple regions can be modeled simultaneously with multilevel models. The models and framework behind
the package are described in Bhatt et al. (2021) <arXiv:2012.00394>. The design of the package has been inspired by, and has borrowed from,
'rstanarm' (Goodrich et al., 2020) <https://mc-stan.org/rstanarm/>. 'rstan' (Stan Development Team, 2020) <https://mc-stan.org/> is used as
the back end for fitting models.

James Scott

epidemia

Modeling of Epidemics using Hierarchical Bayesian Models

Axel Gandy

Swapnil Mishra

Juliette Unwin

Seth Flaxman

Samir Bhatt

Jonathan Ish-Horowicz

Leon Wu

Ben Goodrich

Jonah Gabry

Trustees of Columbia University

Paul-Christian Burkner

Triad Sou

Kengo Nagashima

posterior_metrics function

A fitted model object returned by <code><a rd-options='' href='epim'>epim</a></code>.
See <code><a rd-options='' href='epimodel-objects'>epimodel-objects</a></code>.

A string specifying the name of the observations to plot. This should match one
of the names of the response variables in the <code>obs</code> argument used int the call to <code><a rd-options='' href='epim'>epim</a></code>.

posterior_metrics: CRPS, Mean Absolute Error, Median Absolute Error

Description

Usage

Arguments

Value