TSP Version 5.1     by 

• Product Description
• Principal Characteristics
• TSP Commands
  
• What’s New in Version 5.0 and 5.1
• TSP Student Version
  
• Systems Technical Requirements

Product Description

TSP^TM is a complete language for the estimation and simulation of econometric models. It is a world-wide standard for econometric estimation, with over 2000 installations. What follows is a general overview; detailed lists of features and commands can be found elsewhere. TSP stands for "Time Series Processor", although the program is also frequently used for cross section and panel data. TSP happens to be a common acronym with alternative definitions.

 

Principal Characteristics

• Convenient loading of raw data from free format, fixed format, binary, Lotus or Excel files
• Flexible transformations of series using algebraic expressions, with a full set of operators and functions (transcendental, probability, rounding, etc.) 
• Display and save the original and transformed time series; print a table; graphics on DOS, Windows and MacOS; write to external files in many formats
• Single equation estimation using a variety of techniques:
• OLSQ Ordinary least squares (with extensive diagnostics)
• 2SLS Two stage least squares (instrumental variables)
• LIML Limited information maximum likelihood
• AR1 Regression with first-order serial correlation
• PDL (polynomial distributed lag) variables can be included in all these methods, and Shiller distributed lags can be included in OLSQ
• LLAD Least Absolute Deviations regression - minimizes sum of absolute values of residuals, instead of squares of residuals. A robust estimator. Handles quantile and censored quantile estimation. 
  
• LMS Least Median of Squares regression - minimizes the median squared (or absolute value) residual. Another robust estimator, useful for outlier detection. 
  
• Retrieval of coefficient, residuals, predicted dependent variables, and other test statistics from these estimators for later use 
  
• Estimation of equation systems by simultaneous methods:
• LSQ least squares, minimum distance, nonlinear least squares, multivariate regression and three-stage least squares, both linear and nonlinear
• GMM Generalized method of moments estimation (multiple equation, nonlinear, panel data)
• FIML Estimation of a complete nonlinear simultaneous model by the full information maximum likelihood method
• Extensive hypothesis testing facilities available following any estimation command.
• Simulation, either dynamic or static, of an estimated nonlinear or linear simultaneous model
• Time Series methods:
• BJ Box Jenkins identification, estimation and forecasting
• KALMAN Kalman Filter (State Space) estimation
• ARCH ARCH, GARCH, GARCH-M models of autoregressive conditional heteroskedasticity
• VAR Vector autoregressive models
• COINT for unit roots, Engle-Granger and Johansen trace tests for cointegration
• Maximum likelihood and qualitative dependent variable estimation:
• PROBIT Binary probit model
• TOBIT Tobit (0/+) model
• SAMPSEL Sample selection model (generalized Tobit)
• LOGIT Conditional, multinomial, and mixed logit for two or more choices
• ORDPROB Ordered probit model
• INTERVAL Interval regression (ordered probit with category boundary values known)
  
• POISSON Poisson model for count data
• NEGBIN Negative Binomial models for count data
• ML User-programmed likelihood functions with automatically generated analytic derivatives, examples for Box-Cox, frontier production, nested logit, switching regression, bivariate probit
• Panel Data estimation, fixed and random effects for balanced or unbalanced data
• In addition, TSP's special features give user flexibility in extending the program:
• Ease in handling of multi-sectoral data and equations
• Full matrix algebra including linear programming
• Control of program flow by logical expressions and tests, GOTO statements, and loops
• User-written procedures, callable with arguments
• Random number generation for many distributions: normal, multivariate normal, Cauchy, Student's t, Laplace, exponential, Poisson, negative binomial, gamma, uniform, empirical (bootstrap)
• Extensive library of TSP procedures, developed to solve special econometric problems.

• 16 variables x 1000 observations
• 16 variables x 20 years x 50 states

System Technical Requirements

The following platforms are currently supported by TSP 5.1.

• TSP/Oxmetrics - Windows 95/98/NT/2000/XP/Vista/7
• TSP without Oxmetrics - Windows 95/98/NT/2000/XP/Vista/7
• DOS/Win - DOS, Windows 3.x/95/98/NT/2000
  
• MacOS – up to version 10.6

• Unix
  

TSP/Oxmetrics - Windows 95/98/NT/2000/XP/Vista/7

This runs under 32-bit versions of Windows, in conjunction with the GiveWin interface program. It has the best graphics of all the versions of TSP. It also includes standalone copies of TSP (both Win32 and "extended DOS") which can be run directly from the command prompt, and TSP Through the Looking Glass (TLG). TSP/GiveWin was updated in 3/2000 to run under Windows 2000 (Windows 2000 is not required; the older versions of Windows work fine for TSP/GiveWin).

TSP without Oxmetrics - Windows 95/98/NT/2000/XP/Vista/7

This does not include the Oxmetrics interface, but does include everything else listed above under TSP/Oxmetrics - Win32 TSP and DOS/Win TSP. Note that Win32 TSP does not produce graphics. If you already have a copy of Oxmetrics 2.0 or higher, you can order this and get the Oxmetrics 2.30 upgrade and the TSP Module license without having to pay for Oxmetrics a second time. 

DOS/Win - DOS, Windows 3.x/95/98/NT/2000

This version runs under DOS and as an "extended DOS" application under all flavors of Windows (until XP) as well as OS/2. It allows on-screen editing in interactive mode - you can use arrow keys to repeat and edit commands. It also has full-screen graphics.

System Requirements: Pentium or 486 and...

• 4mb RAM (DOS or Windows 3.x)
• 8mb RAM (Windows 95/98)
• 16mb RAM (Windows NT 3.5/4.0/2000/XP)

Mac OS

This version runs on most MAC OS, although a Rosetta translator add-on is needed for Snow Leopard (version 10.6). If Rosetta is not present on the user's machine, when they first run TSP they will be automatically prompted to download/install it (assuming their Mac is connected to the internet). If they upgraded their Mac to Snow Leopard from an earlier OS, it is on the system install disk as an optional install.

Two versions of TSP are included on the MacOS X CD (released 7/28/2010).

• A standard interface version, with graphics and an Open File dialog box for selecting a batch input file or running in interactive mode.
  
• A Terminal version, which runs from the Terminal application (under Applications/Utilities) and behaves like a standard unix shell.
  

UNIX SYSTEMS

TSP is currently shipping on the following Unix platforms.

• Sun Solaris 2.x, Solaris 8
• Intel Linux (pretty much all standard 32-bit releases of Linux)
  Partial list of known Linux versions which TSP runs on:
  Debian 2.x, libc6/glibc, mandrake 8.2, 9.0, Red Hat 5.x, 6.x, 7.x, 8.x, 9.x, Suse 8.1 
• IBM RS/6000 AIX 5.1 (64-bit and 32-bit versions are available) 
  

All the above have gnuplot graphics. 

• DEC Alpha Digital UNIX 4.0 
  
• HP 9000 HP-UX 10.20 and 11.0 
  

Since system requirements for Unix can be highly idiosyncratic, please contact us if you have specific questions on whether your machine can run TSP or not.

Other Mainframe Systems

TSP 4.5 could be ported to the following DEC VMS systems, if there is interest:

• Alpha/OpenVMS
• VAX/VMS

HARD DRIVE SPACE REQUIRED

On all platforms the TSP application (TSP.EXE on PCs) requires about 2mb of hard drive space when decompressed. TSP/Oxmetrics, Win32 TSP, and the TSP help system may require up to 10mb.

© Copyright 2010 TSP International, Inc.