| OxMetrics
Enterprise Edition |
|
|
|
|
OxMetrics
Enterprise Edition™ is a single product that includes
and integrates all the important components for theoretical
and empirical research in econometrics, time series analysis
and forecasting, applied economics and financial time series:
Ox Professional™, PcGive™, STAMP™ and G@RCH™.
Purchasing
the OxMetrics Enterprise Edition™ will provide users
with a very powerful and cost effective tool to use during
their modelling work. In addition to the usual features
in modern econometric software, OxMetrics Enterprise includes
Autometrics™ (in PcGive), a powerful Automatic Model
Selection procedure..
OxMetrics
Documentation
Ox Professional™
is an object-oriented matrix programming language. It is
an important tool for statistical and econometric programming
with syntax similar to C++ and a comprehensive range of
commands for matrix and statistical operations. Ox is at
the core of OxMetrics. Most of the other modules of OxMetrics
(e.g. PcGive™, STAMP™, G@RCH™) are implemented
with the Ox language. Ox Professional belongs to the OxMetrics
Enterprise Edition™.
New features of Ox Professional™ 6
The
major improvement in Ox is the support of recession shading
in graphs.
Other improvements are minor or bug fixes.
PcGive™
is an essential tool for modern econometric modelling. PcGive™
Professional is part of OxMetrics Enterprise Edition™
and provides the latest econometric techniques, from single
equation methods to advanced cointegration, static and dynamic
panel data models, discrete choice models and time-series
models such as ARFIMA, and X-12-ARIMA for seasonal adjustment
and ARIMA modelling. PcGive™ is easy to use and flexible,
making it suitable both for teaching and research. Very
importantly, PcGive 13 includes Autometrics™, a powerful
automatic model selection procedure. It also includes extensive
facilities for model simulation (PcNaive™). PcGive™
13 now incorporates Markov Switching Models.
New
features in PcGive™ 13
- Regime
switching models: Markov Switching (see detailed exposition
in pdf file). - Diagnostic testing (single and multiple
equations modelling). There are some new tests, the degrees
of freedom have changed on the Heteroscedasticity and ARCH
tests, and some further changes:
•
Added RESET23 and Vector RESET/RESET23 tests. The RESET23
uses squares and cubes, and replaces RESET (just using squares)
in the test summary.
• Added p-values for the Portmanteau statistic; Portmanteau
is omitted from the system test summary if it has an open
lag structure.
• The Hetero-test now removes variables that are identical
when squared (these were already removed from the output,
now they are removed from the calculations - this is useful
when many dummies are present). Also removed are observations
with (almost) zero residuals, removing implicit dummy variables
from the set of regressors. For 4 or more equations the
rotated form is used (n equations instead of n (n+1)/2).
The unrestricted/fixed variables are now always included
in the test.
• The Hetero and ARCH degrees of freedom in the denominator
now exclude k, the original regressor count. The Hetero
test changed from F(s, T-s-1-k) to F(s, T-s-1), while the
ARCH test changed from F(s, T-2s-k) to F(s, T-2s). •
Added Index and Vector Index test. The Index test removes
variables that are identical when cubed. The Index test
is a powerful new low-dimensional test for non-linearity
developed by Jennifer L. Castle and David F. Hendry.
• Added Hetero, Index and RESET23 to PcNaive
• Multiple equation modelling: the single equation
AR and Hetero tests only use variables with non-zero coefficients
in the reduced form. The single equation diagnostic are
now ordered by equation.
Automatic
model selection using Autometrics
•
Autometrics added to cross-section modelling
• Autometrics for binary logit/probit and for count
data
• Autometrics can impose sign restrictions on the search
space. In a dynamic model these are long-run restrictions.
Effectively, models with ‘the wrong signs’ can
be omitted from the search space. Optionally, variables
can be forcefully removed if they are significant with the
wrong sign.
• PcNaive can now run with Autometrics and impulse
saturation, but dummies are not reported in the output.
• Small change to Autometrics output: stages more clearly
identified; now including coefficients of terminal models
as well as p-values. Added sigma to the Autometrics single
equation output (Not Adj.R^2, but note that highest Adj.R^2
corresponds to smallest sigma). Robust standard errors (single
and multiple equations modelling): Selection of robust standard
errors (HCSE, HACSE) has moved from Options to the estimation
dialog (it is different covariance estimator). Now it is
remembered when it is used, and also part of the generated
Ox code. The tabular output with different robust standard
errors is still available from Further Output; this can
be switched on permanently through Options. The part of
the Options dialog that is below the maximization settings
now purely relate to output options.
http://www.doornik.com/pcgive/
It's
a part of PcGive for designing Monte Carlo experiments of
dynamic econometric models.
There
is a set of interactive dialogs in which the data generation
process (DGP) and model are formulated, and the statistics
of interest are selected. PcNaive then generates and runs
an Ox program. The output appears in GiveWin and can include:
. theoretical analysis of the DGP,
. live graphical output as the experiment progresses,
. numerical output of final results.
PcNaive, included in PcGive comes with a 200 page book,
containing extensive tutorials introducing Monte Carlo analysis,
and showing how the program can be used. A separate part
discusses how PcNaive can be used in teaching econometrics,
starting from the elementary through intermediate and finally
advanced econometrics.
The
book concludes with a comprehensive introduction to the
theory of Monte Carlo analysis, including asymptotic analysis
and response surfaces. Many econometric examples are used
throughout, and the book covers important material which
is often missing from standard text books.
PcNaive
site
STAMP™
is a module designed to model and forecast time series,
based on structural time series modelling. Structural time
series models find application to a variety of fields including
macro-economics, finance, medicine, biology, engineering,
marketing and many other areas. These models use advanced
techniques, such as Kalman filtering, but are set up in
an easy-to-use interface - at the most basic level all that
is required is some appreciation of the concepts of trend,
seasonal and irregular components. The hard work is done
by the program, leaving the user free to concentrate on
model formulation and forecasting. STAMP includes both univariate
and multivariate models and automatic outlier detection.
STAMP is part of OxMetrics Enterprise Edition™.
New
features in STAMP™
- STAMP 8.3 works
under OxMetrics 6.1.
- The Ox code
generator is introduced and fully supported
by STAMP. This new facility can generate
Ox code for the model that is estimated
in STAMP. It complements the Batch code
generator in STAMP. It is particularly useful
for those who use Ox for time series analysis
in a production environment.
- The online
help facility of STAMP is updated. In particular,
the online help for the Batch language and
the new Ox code generator are rewritten.
Solved problems
- All weights
and related computations in the Test/Weights
dialog can be carried out, also for time
series with missing data.
- The Write forecasts
option is combined with a Store forecasts
option in the Test/Forecasting dialog. The
observations forecasts are stored after
confirmation as a new variable with the
forecasts attached at the end of the sample.
When necessary, the database sample is automatically
extended such that the forecast window is
included. The in-sample values of the new
variable are the same as in the original
series.
- The Edit/Save
forecasts option in the Test/Forecasting
dialog is reactivated for model without
explanatory variables.
- The Batch code
options for Forecasting is extended; see
Batch documentation.
- Variables and
components in the Batch code need to be
written between accolades. Specifically,
in the setcmp batch command we have "level",
"slope", "seasonal",
"cycle", "ar" and "irregular".
- Inclusion of
lagged dependent variables is discouraged.
A new facility will be built in for the
next version. In this version it is best
to treat and to have it as an exogenous
variable.
http://stamp-software.com/
G@RCH is a module dedicated to the estimation and
the forecasting of univariate and multivariate (G)ARCH
models and many of its extensions. The available univariate
models are all ARCH-type models. These include ARCH, GARCH,
EGARCH, GJR, APARCH, IGARCH, RiskMetrics, FIGARCH , FIEGARCH
, FIAPARCH and HYGARCH. They can be estimated by approximate
(Quasi-) Maximum Likelihood under one of the four proposed
distributions for the errors (Normal, Student-t , GED
or skewed-Student). Moreover, ARCH-in-mean models are
also available and explanatory variables can enter the
conditional mean and/or the conditional variance equations.
G@RCH 6.0 offers some multivariate GARCH specifications
including the scalar BEKK, diagonal BEKK, full BEKK, RiskMetrics,
CCC, DCC, DECO, OGARCH and GOGARCH models. Finally, h-steps-ahead
forecasts of both equations are available as well as many
univariate and multivariate miss-specification tests (Nyblom,
Sign Bias Tests, Pearson goodness-of-fit, Box-Pierce,
Residual-Based Diagnostic for conditional heteroscedasticity,
Hosking’s portmanteau test, Li and McLead test, constant
correlation test, …).
New
features in G@RCH™
New features of G@RCH 6.1- Bug fixed:
Thanks to Charles Bos and Janus Pawel, a
bug in theestimation of the EGARCH with
Student-t errors has been fixed.- A new
DCC model is available.
**
G@RCH™
6.0 is not only a bug-fix upgrade but includes a new module,
called RE@LIZED.
The
new version includes:
Bug fixed: G@RCH experienced convergence problems when
returns were not expressed in %. This is now fixed.
G@RCH
proposes a new module called RE@LIZED whose aim is to
provide a full set of procedures to compute non-parametric
estimates of the quadratic variation, integrated volatility
and jumps using intraday data. The methods implemented
in G@RCH 6.0 are based on the recent papers of Andersen,
Bollerslev, Diebold and coauthors, Barndorff-Nielsen and
Shephard and Boudt, Croux and Laurent. They include univariate
and multivariate versions of the realized volatility,
bi-power-variation and realized outlyingness weighted
variance. Daily and intradaily tests for jumps are also
implemented. The `Realized' class allows to apply these
estimators and tests on real data using the Ox programming
language. Importantly, they are also accessible through
the rolling menus of G@RCH. Interestingly, like for the
other modules, an Ox code can be generated after the use
of the rolling menus. The Model/Ox Batch Code command
(or Alt+O) activates a new dialog box called `Generate
Ox Code' that allows the user to select an item for which
to generate Ox code.
Non-parametric and parametric intraday periodicity
filters are also provided.
The
DCC-DECO model of Engle and Kelly (2008) is now documented
in the manual. Conditional means, variances, covariances
and correlations of MGARCH models can now be edited in
a basic matrix or array editor.
Bug
fixed (thanks to Charles Bos). Several functions of the
MGarch class had not been included in the oxo file, e.g.
GetVarf_ vec, Append_ in, Append_ out, etc. Bug fixed.
DCC models: the empirical correlation matrix used when
applying ‘Correlation Targeting’ was computed
on the residuals and not the devolatilized residuals as
it should be.
http://www.garch.org/
It was an automatic econometric
model selection program. It's no more developed as stand
alone software but many of the features have been included
in PcGive Professional.
TSP™
is an econometric software package with convenient input
of commands and data, all the standard estimation methods
(including non-linear), forecasting, and a flexible language
for programming your own estimators. TSP is available as
an add-on to OxMetrics™. TSP and TSP/OxMetrics™
offers a wide variety of facilities, such as: single-equation
estimation (using a variety of techniques), nonlinear 3SLS,
GMM and FIML, time series methods (Box-Jenkins, Kalman-filter
estimation, vector autoregressive models, etc.), financial
econometrics (ARCH, GARCH, GARCH-M, including logarithmic
versions), general maximum likelihood, qualitative dependent
variable estimation, and panel data estimation. Extensive
libraries of TSP procedures are available free of charge.
New
Features in TSP/OxMetrics 5.1
In addition
to the OxMetrics™ interface, a number of enhancements
have been made to this release of TSP, which we describe
here. The major and minor enhancements to various procedures
are listed here:
• VAR - Generalized Impulse Response and improved plotting
• LSQ, ML, and PROBIT – Panel-robust (clustered)
standard errors
• ANALYZ for functions of series, improved output and
options
• LP – new linear programming procedure
• SORT – speed enhancements
• LAD and LMS - enhanced iteration, looking for multiple
solutions
• LIML – added the log likelihood (used for testing)
• FORM – ability to create unnormalized equations
• New stepsize option for nonlinear procedures, improving
iteration behavior.
• GRAPH – circle plots (where importance of each
point is shown) added
There are also a number of general enhancements: greatly
improved Excel
spreadsheet reading with more versions and multiple sheets,
reading of Stata.dta
files up to Version 10, ability to label matrices rows and
columns when they are
printed, more informative output from SHOW SERIES, and more
efficient long
programs with loops.
http://www.tspintl.com/
| 
