Showing 10 of total 10 results (show query)
atsa-es
MARSS:Multivariate Autoregressive State-Space Modeling
The MARSS package provides maximum-likelihood parameter estimation for constrained and unconstrained linear multivariate autoregressive state-space (MARSS) models, including partially deterministic models. MARSS models are a class of dynamic linear model (DLM) and vector autoregressive model (VAR) model. Fitting available via Expectation-Maximization (EM), BFGS (using optim), and 'TMB' (using the 'marssTMB' companion package). Functions are provided for parametric and innovations bootstrapping, Kalman filtering and smoothing, model selection criteria including bootstrap AICb, confidences intervals via the Hessian approximation or bootstrapping, and all conditional residual types. See the user guide for examples of dynamic factor analysis, dynamic linear models, outlier and shock detection, and multivariate AR-p models. Online workshops (lectures, eBook, and computer labs) at <https://atsa-es.github.io/>.
Maintained by Elizabeth Eli Holmes. Last updated 1 years ago.
multivariate-timeseriesstate-space-modelsstatisticstime-series
52 stars 10.34 score 596 scripts 3 dependents
nicholasjclark
mvgam:Multivariate (Dynamic) Generalized Additive Models
Fit Bayesian Dynamic Generalized Additive Models to multivariate observations. Users can build nonlinear State-Space models that can incorporate semiparametric effects in observation and process components, using a wide range of observation families. Estimation is performed using Markov Chain Monte Carlo with Hamiltonian Monte Carlo in the software 'Stan'. References: Clark & Wells (2023) <doi:10.1111/2041-210X.13974>.
Maintained by Nicholas J Clark. Last updated 22 hours ago.
bayesian-statisticsdynamic-factor-modelsecological-modellingforecastinggaussian-processgeneralised-additive-modelsgeneralized-additive-modelsjoint-species-distribution-modellingmultilevel-modelsmultivariate-timeseriesstantime-series-analysistimeseriesvector-autoregressionvectorautoregressioncpp
148 stars 9.92 score 117 scripts
fchamroukhi
samurais:Statistical Models for the Unsupervised Segmentation of Time-Series ('SaMUraiS')
Provides a variety of original and flexible user-friendly statistical latent variable models and unsupervised learning algorithms to segment and represent time-series data (univariate or multivariate), and more generally, longitudinal data, which include regime changes. 'samurais' is built upon the following packages, each of them is an autonomous time-series segmentation approach: Regression with Hidden Logistic Process ('RHLP'), Hidden Markov Model Regression ('HMMR'), Multivariate 'RHLP' ('MRHLP'), Multivariate 'HMMR' ('MHMMR'), Piece-Wise regression ('PWR'). For the advantages/differences of each of them, the user is referred to our mentioned paper references. These models are originally introduced and written in 'Matlab' by Faicel Chamroukhi <https://github.com/fchamroukhi?&tab=repositories&q=time-series&type=public&language=matlab>.
Maintained by Florian Lecocq. Last updated 5 years ago.
artificial-intelligencechange-point-detectiondata-sciencedynamic-programmingem-algorithmhidden-markov-modelshidden-process-regressionhuman-activity-recognitionlatent-variable-modelsmodel-selectionmultivariate-timeseriesnewton-raphsonpiecewise-regressionstatistical-inferencestatistical-learningtime-series-analysistime-series-clusteringopenblascpp
11 stars 6.14 score 28 scripts
tsmodels
tsmarch:Multivariate ARCH Models
Feasible Multivariate Generalized Autoregressive Conditional Heteroscedasticity (GARCH) models including Dynamic Conditional Correlation (DCC), Copula GARCH and Generalized Orthogonal GARCH with Generalized Hyperbolic distribution. A review of some of these models can be found in Boudt, Galanos, Payseur and Zivot (2019) <doi:10.1016/bs.host.2019.01.001>.
Maintained by Alexios Galanos. Last updated 6 days ago.
econometricsfinancegarchmultivariate-timeseriestime-seriesopenblascpp
7 stars 5.80 score 3 scripts
gmgeorg
ForeCA:Forecastable Component Analysis
Implementation of Forecastable Component Analysis ('ForeCA'), including main algorithms and auxiliary function (summary, plotting, etc.) to apply 'ForeCA' to multivariate time series data. 'ForeCA' is a novel dimension reduction (DR) technique for temporally dependent signals. Contrary to other popular DR methods, such as 'PCA' or 'ICA', 'ForeCA' takes time dependency explicitly into account and searches for the most ''forecastable'' signal. The measure of forecastability is based on the Shannon entropy of the spectral density of the transformed signal.
Maintained by Georg M. Goerg. Last updated 5 years ago.
blind-source-separationdimensionality-reductionforecastingmultivariate-timeseriessignal-processingspectrumtime-seriestime-series-analysis
15 stars 5.47 score 39 scripts
aniebee
ClusterVAR:Fitting Latent Class Vector-Autoregressive (VAR) Models
Estimates latent class vector-autoregressive models via EM algorithm on time-series data for model-based clustering and classification. Includes model selection criteria for selecting the number of lags and clusters.
Maintained by Anja Ernst. Last updated 3 months ago.
clusteringlatent-class-modelmultivariate-timeseriestime-series-analysisvector-autoregressionvector-autoregression-models
2 stars 4.88 score 1 scriptsatsa-es
tvvarss:Time Varying Vector Autoregressive State Space Models
The tvvarss package uses Stan (mc-stan.org) to fit multi-site multivariate autoregressive (aka vector autoregressive) state space models with a time varying interaction matrix.
Maintained by Eric Ward. Last updated 3 years ago.
bayesianmultivariate-timeseriesstate-spacetime-seriescpp
10 stars 4.04 score 11 scriptsatsa-es
marssTMB:Fast fitting of MARSS models with TMB
Companion to the MARSS package. Fast fitting of MARSS models with TMB. See the MARSS documentation. All the model syntax and features are the same as for the MARSS package.
Maintained by Elizabeth E. Holmes. Last updated 2 years ago.
marssmultivariate-timeseriesstate-space-modeltime-seriestmb
1 stars 3.68 score 19 scriptsatsa-es
varlasso:Vector Autoregressive State Space Models With Shrinkage
The varlasso package uses Stan (mc-stan.org) to fit VAR state space models with optional shrinkage priors on B matrix elements (autoregression coefficients).
Maintained by Eric Ward. Last updated 3 years ago.
bayesianmultivariate-timeseriestime-seriescpp
2 stars 3.00 score 2 scriptsatsa-es
MAR1:Multivariate Autoregressive Modeling for Analysis of Community Time-Series Data
The MAR1 package provides basic tools for preparing ecological community time-series data for MAR modeling, building MAR-1 models via model selection and bootstrapping, and visualizing and exporting model results. It is intended to make MAR analysis sensu Ives et al. (2003) Analysis of community stability and ecological interactions from time-series data) a more accessible tool for anyone studying community dynamics. The user need not necessarily be familiar with time-series modeling or command-based statistics programs such as R.
Maintained by Elizabeth Eli Holmes. Last updated 2 years ago.
multivariate-timeseriestime-series
1 stars 3.00 score