Using Sabre: Introduction

Sabre manual

The current release of SABRE contains forty two commands. These commands are specifically designed to be useful for the analysis of binary, Poisson, continuous or ordinal recurrent events and, consequently, we have avoided the provision of general statistical procedures that are already available in many other packages.

Before using SABRE, users should be aware of some general points:

  • Only the first six characters of a command are recognised, although more letters may be given. Commands can be abbreviated, provided that they remain uniquely identified, but must always be at least 3 characters long. Thus, the command YVARIATE can be shortened down to YVA, but the command TRANSFORM can only be shortened down to TRAN since TRA is ambiguous with TRACE.
  • Where appropriate, command lines may be continued on subsequent lines using the continuation symbol '&' at the end of each line to be continued.
  • Each command must start on the first position of the line and only one command is allowed per line.
  • Command arguments must be separated from their command by at least one space. Similarly, arguments must be separated from each other by spaces.
  • Names of variables or factors must not start with an integer, a dollar sign($) or an ampersand(&) and the names 'exp', 'log' and 'cons' are not permitted.
  • There is no distinction between upper and lower case characters. Thus, for example, SABRE is unable to distinguish between variables named AVAR and avar.
  • All occurences of the character '$' on the input line are ignored.
We will now describe the use of SABRE during a typical computing session. Although some information on commands will be given, extensive information on syntax is provided in the command reference.

Go to: Sabre home page | Sabre manual | Downloading & Installing Sabre | Sabre examples | Training materials | Sabre mailing list | Contact us

Other links: Centre for e-Science | Centre for Applied Statistics