2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2015
Here we investigate a new concept, kernel-nonlinear-Partial Directed Coherence, whereby a kernel ... more Here we investigate a new concept, kernel-nonlinear-Partial Directed Coherence, whereby a kernel feature space representation of the data allows detecting nonlinear causal links that are otherwise undetectable through linear modeling. We show that adequate connectivity detection is achievable by applying asympotic decision criteria similar to the ones developed for linear models.
After reviewing wavelet techniques used to estimate the long-memory parameter d used in ARFIMA mo... more After reviewing wavelet techniques used to estimate the long-memory parameter d used in ARFIMA models, Monte Carlo simulations are used to evaluate the performance of different discrete wavelet transforms under various mother wavelet choices. By comparing computed small sample bias, standard deviations and mean-square errors from the different methods, MODWPT's (Maximum Overlap Discrete Wavelet Packet Transform) is shown to outperform all other options under a minimum mean-square error criterion using the D(4) wavelet filter.
Infering causal relationships from observed time
series has attracted much recent attention. In c... more Infering causal relationships from observed time series has attracted much recent attention. In cases of nonlinear coupling, adequate inference is often hindered by the need to specify coupling details that call for many parameters and global minimization of nonconvex functions. In this paper we use an example to investigate a new concept, termed here running entropy mapping, whereby time series are mapped onto other entropy related time sequences whose analysis via a linear parametric time series methods, such as partial directed coherence, is able to expose the presence of formerly linearly undetectable causal relationships.
2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2015
Here we investigate a new concept, kernel-nonlinear-Partial Directed Coherence, whereby a kernel ... more Here we investigate a new concept, kernel-nonlinear-Partial Directed Coherence, whereby a kernel feature space representation of the data allows detecting nonlinear causal links that are otherwise undetectable through linear modeling. We show that adequate connectivity detection is achievable by applying asympotic decision criteria similar to the ones developed for linear models.
After reviewing wavelet techniques used to estimate the long-memory parameter d used in ARFIMA mo... more After reviewing wavelet techniques used to estimate the long-memory parameter d used in ARFIMA models, Monte Carlo simulations are used to evaluate the performance of different discrete wavelet transforms under various mother wavelet choices. By comparing computed small sample bias, standard deviations and mean-square errors from the different methods, MODWPT's (Maximum Overlap Discrete Wavelet Packet Transform) is shown to outperform all other options under a minimum mean-square error criterion using the D(4) wavelet filter.
Infering causal relationships from observed time
series has attracted much recent attention. In c... more Infering causal relationships from observed time series has attracted much recent attention. In cases of nonlinear coupling, adequate inference is often hindered by the need to specify coupling details that call for many parameters and global minimization of nonconvex functions. In this paper we use an example to investigate a new concept, termed here running entropy mapping, whereby time series are mapped onto other entropy related time sequences whose analysis via a linear parametric time series methods, such as partial directed coherence, is able to expose the presence of formerly linearly undetectable causal relationships.
Uploads
Papers by Lucas Massaroppe
series has attracted much recent attention. In cases of nonlinear
coupling, adequate inference is often hindered by the need
to specify coupling details that call for many parameters and
global minimization of nonconvex functions. In this paper we
use an example to investigate a new concept, termed here
running entropy mapping, whereby time series are mapped
onto other entropy related time sequences whose analysis via a
linear parametric time series methods, such as partial directed
coherence, is able to expose the presence of formerly linearly
undetectable causal relationships.
series has attracted much recent attention. In cases of nonlinear
coupling, adequate inference is often hindered by the need
to specify coupling details that call for many parameters and
global minimization of nonconvex functions. In this paper we
use an example to investigate a new concept, termed here
running entropy mapping, whereby time series are mapped
onto other entropy related time sequences whose analysis via a
linear parametric time series methods, such as partial directed
coherence, is able to expose the presence of formerly linearly
undetectable causal relationships.