Fitting piecewise linear threshold autoregressive models by means of genetic algorithms

DOI10.1016/j.csda.2003.11.003zbMath1429.62383MaRDI QIDQ957007

Domenico Cucina, Roberto Baragona, Francesco Battaglia

Publication date: 26 November 2008

Published in: Computational Statistics and Data Analysis (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.csda.2003.11.003

zbMATH Keywords

splines; time series; genetic algorithms; sunspot numbers; Canadian lynx data; blowfly population data; self-exciting threshold autoregressive models; state dependent models

Mathematics Subject Classification ID

62-08: Computational methods for problems pertaining to statistics

62M10: Time series, auto-correlation, regression, etc. in statistics (GARCH)

90C59: Approximation methods and heuristics in mathematical programming

Related Items

Time-varying multi-regime models fitting by genetic algorithms, Nonlinearity testing and modeling for threshold moving average models, Structural changes estimation for strongly dependent processes, Evolutionary Computation Methods and their applications in Statistics, Bayesian multiple structural change-points estimation in time series models with genetic algorithm, Applications of optimization heuristics to estimation and modelling problems, A genetic algorithm estimation of the term structure of interest rates, GSA-based maximum likelihood estimation for threshold vector error correction model, Forecasting inflation and GDP growth using heuristic optimisation of information criteria and variable reduction methods, Estimation and identification of periodic autoregressive models with one exogenous variable, An analysis of global warming in the Alpine region based on nonlinear nonstationary time series models, Parsimonious periodic autoregressive models for time series with evolving trend and seasonality, Multi-regime models for nonlinear nonstationary time series, Bayesian subset selection for threshold autoregressive moving-average models, Periodic autoregressive model identification using genetic algorithms, Genetic algorithms for building double threshold generalized autoregressive conditional heteroscedastic models of time series, NONLINEAR TIME SERIES PREDICTION BASED ON A POWER-LAW NOISE MODEL

Uses Software

• TDSL
• Genocop
• AS 183
• TSDL

Cites Work

• Threshold models in non-linear time series analysis
• Genetic algorithms and their statistical applications: an introduction
• Genetic algorithms. Concepts and designs
• ON ESTIMATING THRESHOLDS IN AUTOREGRESSIVE MODELS
• Non-linear threshold autoregressive models for non-linear random vibrations
• Modelling nonlinear random vibrations using an amplitude-dependent autoregressive time series model
• THE STATISTICAL ANALYSIS OF PERTURBED LIMIT CYCLE PROCESSES USING NONLINEAR TIME SERIES MODELS
• Functional-Coefficient Regression Models for Nonlinear Time Series
• Functional-Coefficient Autoregressive Models
• Using genetic algorithms to parameters \((d,r)\) estimation for threshold autoregressive models
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item