penalized_likelihood

Observation matrix (may need to be normalized and centered before hand) (q rows, T columns)

Input matrix for the state equation (m_u rows, T columns)

Input matrix for the output equation (m_v rows, T columns)

a vector of parameter elements (i.e, the vectorized version of theta
in <code>Kalman_smoother</code>)

theta.vec

lambda

<a rd-options="" href="/link/Kalman_smoother?package=ldsr&version=0.0.2" data-mini-rdoc="ldsr::Kalman_smoother">Kalman_smoother</a> returns X and likelihood.
The penalized likelihood is the likelihood minus the sum-of-squares of the
measurement update. This is used as the fitness function in genetic algorihm.

Streamflow (and climate) reconstruction using Linear Dynamical Systems.
The advantage of this method is the additional state trajectory which can reveal more information
about the catchment or climate system. For details of the method please refer to Nguyen and Galelli
(2018) <doi:10.1002/2017WR022114>.

Hung Nguyen

ldsr

Linear Dynamical System Reconstruction

Stefano Galelli

penalized_likelihood function

<a rd-options='' href='Kalman_smoother'>Kalman_smoother</a> returns X and likelihood.
The penalized likelihood is the likelihood minus the sum-of-squares of the
measurement update. This is used as the fitness function in genetic algorihm.

penalized_likelihood: Penalized likelihood objective function

Description

Usage

Arguments

Value