logLik,hspec-method

The log-likelihood of the ground process of the Hawkes model.
(The log-likelihood for mark (jump) distribution is not provided.)

Simulate and fitting exponential multivariate Hawkes model.
This package simulates a multivariate Hawkes model, introduced by Hawkes (1971) <doi:10.2307/2334319>, with an exponential kernel and fits the parameters from the data.
Models with the constant parameters, as well as complex dependent structures, can also be simulated and estimated.
The estimation is based on the maximum likelihood method, introduced by introduced by Ozaki (1979) <doi:10.1007/BF02480272>, with 'maxLik' package.

Kyungsub Lee

emhawkes

Exponential Multivariate Hawkes Model

logLik,hspec-method function

<dl><dt>object</dt>
<dd><code>hspec-class</code>. The parameter values in the object are used to compute the log-likelihood.</dd>
<dt>inter_arrival</dt>
<dd>A vector of realized inter-arrival times of events which includes inter-arrival for events that occur in all dimensions. Start with zero.</dd>
<dt>type</dt>
<dd>A vector of realized dimensions distinguished by numbers, 1, 2, 3, and so on. Start with zero.</dd>
<dt>mark</dt>
<dd>A vector of realized mark (jump) sizes. Start with zero.</dd>
<dt>N</dt>
<dd>A matrix of counting processes.</dd>
<dt>Nc</dt>
<dd>A matrix of counting processes weighted by mark.</dd>
<dt>N0</dt>
<dd>A matrix of initial values of N.</dd>
<dt>lambda_component0</dt>
<dd>The initial values of lambda component. Must have the same dimensional matrix with <code>object</code>.</dd>
<dt>...</dt>
<dd>Further arguments passed to or from other methods.</dd></dl>

Arguments

Compute the log-likelihood function — logLik,hspec-method

<dl>

<dt>object</dt>
<dd><code>hspec-class</code>. The parameter values in the object are used to compute the log-likelihood.</dd>


<dt>inter_arrival</dt>
<dd>A vector of realized inter-arrival times of events which includes inter-arrival for events that occur in all dimensions. Start with zero.</dd>


<dt>type</dt>
<dd>A vector of realized dimensions distinguished by numbers, 1, 2, 3, and so on. Start with zero.</dd>


<dt>mark</dt>
<dd>A vector of realized mark (jump) sizes. Start with zero.</dd>


<dt>N</dt>
<dd>A matrix of counting processes.</dd>


<dt>Nc</dt>
<dd>A matrix of counting processes weighted by mark.</dd>


<dt>N0</dt>
<dd>A matrix of initial values of N.</dd>


<dt>lambda_component0</dt>
<dd>The initial values of lambda component. Must have the same dimensional matrix with <code>object</code>.</dd>


<dt>...</dt>
<dd>Further arguments passed to or from other methods.</dd>

</dl>

logLik,hspec-method: Compute the log-likelihood function

Description

Usage

Arguments

See Also