What's new in RATS 10.0

Version 10 of RATS is now available.

A list with all combined changes after 9.0 through 10.0 is listed on the RATS website.

Here are some highlights taken from the version 10 release upgrade:

• CALENDAR now allows for irregular input dates to handle daily data with skipped entries for holidays while maintaining the ability to use dates on input and output. The DATA instruction has a JULIAN option which pulls that information from a date column on the file, while several new functions will compute the required information from information coded in other ways (such as separate year, month and day fields on the file). In particular, GRAPH can now show dates on graphs with irregular dated data.
• The Data (Other Formats) Wizard now includes handling for name overrides if the name on the file isn't permitted by RATS (for instance, name fields with blanks) or is long or cryptic. The Box-Jenkins (ARIMA), ARCH/GARCH(Univariate) and ARCH/GARCH(Multivariate) Wizards have all been converted to use tabs to reduce clutter.
• GARCH allows DISTRIB=GED on multivariate models (not just univariate) and adds the DCC and QBAR options to control the secondary recursion for the DCC model.
• ERRORS, IMPULSE and HISTORY, which require fully linear models for their calculations, will now accept models with simple FRML's if those are in a linear form (typically for identities which are often easier to write as FRML's).
• HISTORY has new BASE and EFFECTS options which are an easier-to-use way to obtain the breakdown of the historical decomposition.

Updated Manuals

• We added more information in the User's Guide chapters on "ARCH/GARCH and related models", "Threshold, Breaks and Switching" and "Cross Section and Panel Data". This partly reflects the fact that these were the topics of our three most recent e-courses, and the GARCH and panel data instructions saw quite a bit of change as a result. Also GARCH and the regime-switching models can often require a bit of care to get reasonable results (or results at all), which has produced many of our technical questions in recent years. As much as possible, we try to address those issues in the revised documentation.

Interface Improvements

• The online help feature has been completely revised. It now has the full content of the Reference Manual, with some important extras: over 100 of the most important procedures with a full description of syntax and examples. It is also fully linked up with cross-references for ease of use.
• The GARCH wizard has been split into separate wizards for univariate and multivariate models. A new wizard for handling estimation of cointegration models provides easy-to-use access to the @JOHMLE, @FM and @SWDOLS procedures.
• File-Properties shows the full file name of an open file (in a form where you can easily copy and paste). This can be handy when you have long paths so the name gets truncated.
• Help-News... gets a "news feed" off our web site with links to updated information.
• With version 8.3, we replaced the editor which actually runs most of the program with a new public domain editor called Scintilla. This adds the ability to put markers at locations in your program and includes "regular expressions" for more sophisticated searches. A few oddities in its operation (particularly skipping lines if you hold down the Enter key) have been corrected with version 9.
• Another important change with v8.3 that’s even better with v9 is Find in Files. This allows you to search for a string (or "regular expression") across the full set of example programs so you can quickly locate example programs that use DLM or do a BEKK GARCH or an SPGRAPH,etc. It gives a huge boost to your productivity.

Programming Updates

• The most important change to the program itself is that you can now pass functions as parameters and options.This was a big hole in the RATS programming language–we haven’t even begun to figure out all the things that will be made easier or (even) possible using this.
• We introduced the HASH and LIST aggregators with version 8.2, but with version 9, we’ve added enough support to these to make them truly useful. These have been added to the documentation and examples of their use is now included.
• The diagnostics for attempts to access out-of-range array elements have been improved, pointing you towards the likely source. You also now get better information about mistyped identifiers, as the program will list possible near-matches.

Changes to Instructions

• You can now write data to XLSX and not just XLS. This applies to any instruction which writes data and to the export operations from REPORT windows.
• SPGRAPH can now put keys out the outside of a matrix of graphs.
• The GARCH instruction adds the new option VARIANCES=KOUTMOS to compute the univariate variances for CC and DCC models using the EGARCH formulation from Koutmos(1996) "Modeling the Dynamic Interdependence of Major European Stock Markets", Journal of Business Finance and Accounting, vol 23, 975-988. It also adds the STDRESIDS option for computing standardized residuals (univariate or jointly standardized multivariate).
• IMPULSE has a new FLATTEN option for more easily saving into %%RESPONSES in Monte Carlo methods. Its FACTOR option can accept reduced numbers of columns (shocks), which makes it easier to handle situations where you are particularly interested in only a subset of the structural shocks.
• HEIGHT and WIDTH have been added to GRPARM to allow standardized sizing of graphs.
• GRAPH has a new SERIES option which can take a VECTOR of SERIES or a VECT[INTEGER] with series handles as input. This is particularly handy for doing graphics in Vector Autoregressions, where the number of graphs needed can change from application to application.
• The DATA instruction adds the new option ORG=MULTILINE which allows you to pull data out of a spreadsheet file when a particular series occupies a block of rows.

New in RATS 8.3

RATS version 8.3 includes several important new tools to make you more productive.

With rats version 8.3, several important new tools have been added to make you more productive. RATS is now using a public domain "programmer's editor" called Scintilla. We've used a proprietary text editor since WinRATS was introduced, as the text editor supplied with Windows at the time was limited to 32K bytes, which could be completely filled with one set of impulse responses on a reasonably large model. Unfortunately, that editor was orphaned several years ago, and wasn't portable to the Macintosh or Unix.

Scintilla is portable to all three platforms and is specifically designed as a programmer’s editor, which is what is needed for rats. One very useful feature is a “bracket matcher”, which shows the (apparent) matches for ( ) and { } pairs (showing the mates in green), to help fix parenthesis nesting errors. If one of these characters has no obvious partner, it is shown in red as you cursor over it. We’ve also added the ability to “mark” a location in a text file so you can easily return to it.

A big productivity aid is the new Find in Files operation. Among standard, textbook and paper replication examples, we have well over 1000 running examples. With Find in Files, you can search across these for particular text, like MV=DCC to find examples which do dcc garch models. Both Find in Files, and the standard Edit-Find operations also now support “regular expressions”, a standard set of codings for text patterns. For instance, a search pattern of sur(.*model= will locate all instances of a SUR instruction with the MODEL option, with.* matching any number of characters. A simple sur(model= will only find examples where MODEL is the first option listed.

RATS 8.3 now uses multiple “threads” with the editor interface in one and the statistical engine in another. This makes it possible for the editor part to still be responsive while calculations are going on. It also slightly improves performance, particularly on computers with multiple cores, since it can give over one entire core to the numerical calculations while running the interface (and anything else you’re doing) on another.

The 64-bit executable (on WinRATS Pro) now runs about 15-20% faster than the 32-bit on the same computer due to improvements in compiler technology. We still provide both executables, since some of the added data formats aren’t available for the 64-bit at this point. The install process for Win-RATS Pro has been simplified, with the downloadable version now including both 32 and 64 bit.

The following changes have been made to existing instructions:

• BOXJENK has a MEANEQ option to define the equation for the mean (only) in a RegARIMA model
• SSTATS adds a START option similar to those on SET and MAXIMIZE. It also will now ignore entries which evaluate to NA so you don’t have to use a SMPL option to skip over them.
• THEIL now has a FORECASTS option which allows you to input a set of forecasts generated by some method other than the standard techniques available, while still being able to let THEIL do the forecast error calculations.
• The STACKED bar graph styles on GRAPH will now allow a mix of positive and negative values at a given time period, stacking away from zero in each direction.
• The VTICKS and HTICKS options on the graphics instructions will now accept a VECTOR of values at which you want tick marks, allowing you to override the automatic choices made by rats.

8.3 adds several new functions:

• %MODELLARGESTROOT(model) returns the absolute value of the largest root of the companion matrix of a model. This is helpful in doing Monte Carlo simulations on a var, as you can easily reject draws that are unstable.
• %STRESCAPE(s,chars,escape) returns a string with any character from chars “escaped” by prefixing with it the character or string escape.
• %STRFIND(s,f) looks for the string f in s, returning the position if found and zero otherwise
• %STRTRIM(s) returns a copy of a string with leading and trailing quotes and spaces removed

In addition, quite a few existing functions have been altered to allow them to apply to each element of a vector or matrix rather than just to single real values: COS, SIN, TAN, %PLUS and %MINUS. %VALID, when applied to a matrix will return 1 only if no element of the matrix is missing.

See the October 2013 RATSLetter for more details.

New in RATS 8.2

• expanding graphing capabilities including the ability to specify an exact graph size, an easier way to graph arrays of series, and a new instruction for automatically saving graphs.
• new options on SUMMARIZE that make it easier to examine non-linear functions of estimated parameters, including non-linear estimation parameters, and to use numerical rather than analytical derivatives to deal with functions for which RATS has no analytical derivatives.
• a new option on FIND for doing grid searches, which is particularly useful for threshold models.
• support for some additional multivariate GARCH models, as well as more flexible handling of asymmetric effects.
• a new "Cointegration Tests" wizard.
• two new variable types for more flexible handling of vectors.
• dozens of new procedures and example programs.

See the September 2012 RATSletter for more details.

New in RATS 8.1

New in RATS 8.0

RATS Version 8 was a major update featuring a new look, new manuals, improved data handling, more powerful tools for organizing results, and much more.

Revised Manuals

• Completely revised manuals, including a new 180-page Introduction to RATS.
• Updated Reference Manual.
• Expanded User's Guide with more coverage of state space and DSGE models, switching models and structural breaks, Vector Autoregressions, and Simulations and Bootstrapping.
• Much more extensive cross-referencing.

Interface Improvements

• New View menu operations provide quick access to information on data series.
• Redesigned and expanded toolbar icons.
• Many point-and-click Wizards have new features and are easier to use.
• More control over default arrangement of Input and Output windows.

Data Management

Making it as easy as possible to get data into the program was a major focus in developing RATS 8. Enhancements include:

• Support for more data formats, including Stata®, EViews® and MATLAB® (support for Excel® 2007 was added with 7.3).
• More flexibility for reading spreadsheet files.
• Data Wizard: Can now read in subsets of data or compact/expand data to different frequency (previously required typing in instructions directly).
• Can read series into memory from a RATS file by simply dragging-and-dropping them onto the Series Window.
• Can copy and paste data series data into Series Edit Windows (handy for copying data from web sites or PDF files).
• READ and WRITE support many more formats, including XLS, XLSX, WKS, and MATLAB.

Improved Reports

Another design goal was to extend the Reports features in RATS to make it even easier for you to translate your results quickly and accurately into publications or other applications.

• Almost all output generated by RATS instructions, such as tables of regression coefficients, can now be reloaded in a report window via the Report Windows menu operation.
• Reports can now be reformatted on screen (changing the displayed precision), and then exported or copy-and-pasted in a number of formats.
• TeX Support: Reports can now be exported as a TeX tabular or copied to the clipboard in TeX format for pasting in a TeX editor. User-defined reports can be formatted to include TeX mathematical expressions.
• Most procedures supplied with RATS now save output as "titled" reports, which can be easily recalled for viewing, exporting, or copying and pasting using the Report Windows operation.

Programming Features

• You can define much more complex nested variable structures, such as "arrays of arrays of arrays" or "arrays of series of arrays".
• The %IF function accepts a much wider variety of argument types.

Other New Features

• More than thirty functions have been added since version 7.0.
• New DUMMY instruction for generating standard dummy, trading day, and intervention variables.
• VARIANCES=SPILLOVER option on GARCH for the univariate variance model in a CC or DCC model.
• BACKGROUND option on GRPARM for setting the background color of a graph box.
• RGF option on SPGRAPH allows you to insert an existing graph file into a matrix of graphs.
• Graph windows are now titled using either their header or footer (if available), making it easier to locate a particular window.

Please see the December 2010 RATSletter for more details, including a list of the many new procedures and examples that shipped with 8.0.