graphEstim

This function shows the graphs resulting from the estimation of a HMM model

Inference, goodness-of-fit tests, and predictions for continuous and discrete univariate Hidden Markov Models (HMM), including zero-inflated distributions. The goodness-of-fit test is based on a Cramer-von Mises statistic and uses parametric bootstrap to estimate the p-value. The description of the methodology is taken from Nasri et al (2020) <doi:10.1029/2019WR025122>.

Bouchra Nasri

GenHMM1d

Goodness-of-Fit for Zero-Inflated Univariate Hidden Markov
Models

Mamadou Yamar Thioub

graphEstim function

<dl><dt>y</dt>
<dd>observations</dd>
<dt>ZI</dt>
<dd>1 if zero-inflated, 0 otherwise (default)</dd>
<dt>reg</dt>
<dd>number of regimes</dd>
<dt>theta</dt>
<dd>estimated parameters; (r x p)</dd>
<dt>family</dt>
<dd>distribution name; run the function distributions() for help</dd>
<dt>pred_l</dt>
<dd>estimated regime using lambda</dd>
<dt>pred_e</dt>
<dd>estimated regime using eta</dd></dl>

Arguments

Graphs — graphEstim

<dl>

<dt>y</dt>
<dd>observations</dd>


<dt>ZI</dt>
<dd>1 if zero-inflated, 0 otherwise (default)</dd>


<dt>reg</dt>
<dd>number of regimes</dd>


<dt>theta</dt>
<dd>estimated parameters; (r x p)</dd>


<dt>family</dt>
<dd>distribution name; run the function distributions() for help</dd>


<dt>pred_l</dt>
<dd>estimated regime using lambda</dd>


<dt>pred_e</dt>
<dd>estimated regime using eta</dd>

</dl>

graphEstim: Graphs

Description

Usage

Value

Arguments