Chapter 2: Classic Nonlinear Models
Data Sets
Chapter-2-data.zip
Jokulsa.dat
Oldman-river.dat
USunemplmnt_logistic.dat
USunemplmnt_matrix.dat
Chapter-2-data.zip
Jokulsa.dat
Oldman-river.dat
USunemplmnt_logistic.dat
USunemplmnt_matrix.dat
|
Computer Codes
Examples: Example_2-8.zip Example_2-9.zip Exercises: Exercise_2-9.zip Exercise_2-10.zip Exercise_2-11.zip Exercise_2-12.zip Miscellanea: Gonzalo-Wolf-SETAR.zip GRASP.zip SEASETAR.zip Figures Figures-Chapter-2-exercises.zip Figures-Chapter-2_exercises-jpg.zip |
(M code) (F code and renamed exe file) (R code) (R code) (R code) (M code) (C code) (M code) (F code) (EPS format) (JPEG format) |
Links to Websites with Supplementary Material
- Click on the following link for getting access to computer codes (Ox, MATLAB, and R) and papers related to a class of observation-driven nonlinear time series models referred to as generalized autoregressive score (GAS) models. The mechanism to update the parameters over time is the scaled score of the likelihood function; http://www.gasmodel.com/background.htm.
- Click on the following link for getting access to Marcelo Perlin’s website with MATLAB and R code for estimating Markov regime switching models. The R-MSGARCH package allows the user to perform ML and Bayesian estimation as well as forecasting for a very large class of models.
- Click on the following link for getting access to James Hamilton’s website with data and software (mainly GAUSS) from various studies.
- Click on the following link for getting access to the NNSYSID toolbox (system identification with NNs) for MATLAB, and the NNCTRL toolkit, an add-on for design and simulation of NNs based control systems.
- Click on the following link for getting access to the website accompanying the book by Zivot and Wang (2006), Modeling Financial Time Series with S-Plus (2nd. ed.), Springer-Verlag, New York. Alternatively, R scripts are available at: http://faculty.washington.edu/ezivot/MFTSR.htm.
- Click on the following link for getting access to Simon van Norden's homepage with GAUSS codes and data sets for analyzing switching regressions and Markov mixture models. The website econpapers.repec.org/paper/bcabocawp/96-3.htm provides documentation/information about the computer programs.
- Data and GAUSS computer programs to accompany Kim and Nelson (1999), State-Space Models with Regime-Switching: Classical and Gibbs-sampling approaches with applications (MIT Press) can be downloaded from: econ.korea.ac.kr/~cjkim/MARKOV/prgmlist.htm.
- Click on the following link for getting access to Xiaming Huo's website with MATLAB and R codes for estimating a Hessian regularized nonlinear time series model introduced in Chen and Huo (2009, J. Computational and Graphical Statistics).
- The website unstarched is the home of a number of financial R-packages developed by Alexios Ghalanos. The R-twinkle package (beta version) includes steps for specifying, estimating, testing, and forecasting STAR(MA) models.