The Scythe Statistical Library is an open source C++ library for statistical computation, written by Daniel Pemstein (North Dakota State University), Kevin M. Quinn (Emory University), and Andrew D. Martin (Washington University in St. Louis). It includes a suite of matrix manipulation functions, a suite of pseudo-random number generators, and a suite of numerical optimization routines. Programs written using Scythe are generally much faster than those written in commonly used interpreted languages, such as R and MATLAB, and can be compiled on any system with the GNU GCC compiler (and perhaps with other C++ compilers). One of the primary design goals of the Scythe developers has been ease of use for non-expert C++ programmers. We provide ease of use through three primary mechanisms: (1) operator and function over-loading, (2) numerous pre-fabricated utility functions, and (3) clear documentation and example programs. Additionally, Scythe is quite flexible and entirely extensible because the source code is available to all users under the GNU General Public License.
This document is the application programmer's interface (API) to Scythe. It provides documentation for every class, function, and object in Scythe that is part of the library's public interface. In addition, the sections below explain how to obtain, install, and compile the library.
The most recent version of Scythe is available for download at http://scythe.wustl.edu.
Scythe installs as a header-only C++ library. After uncompressing, simply follow the instructions in the INSTALL file included with Scythe to install the library. Alternatively, you may copy the source files in scythestat and scythestat/rng into your project directory and compile directly, using the SCYTHE_COMPILE_DIRECT pre-processor flag.
Scythe should work with the GNU GCC compiler, version 4.4.7 and greater. Scythe has not been tested with other compilers. Scythe provides a number of pre-processor flags. The SCYTHE_COMPILE_DIRECT flag allows the user to compile Scythe sources directly. The SCYTHE_VIEW_ASSIGNMENT_FLAG flag turns on R-style recycling in Matrix::operator=() for view matrices.
The SCYTHE_DEBUG flag controls the amount of error trapping in Scythe. This level ranges from 0 (virtually no checking) to 3 (all checking, including Matrix bounds checking, turned on). By default, the level is set to 3. Reducing the error check level can substantially improve performance. Here's an example of how to compile a program with only basic error checking:
$ g++ myprog.cc -DSCYTHE_DEBUG=1
The SCYTHE_LAPACK flag enables LAPACK/BLAS support. You must have the LAPACK and BLAS libraries installed on your system and compile your program with the appropriate linker flags for this to work. For example, on linux you can enable LAPACK/BLAS support like this:
$ g++ myprog.cc -DSCYTHE_LAPACK -llapack -lblas -pthread
The SCYTHE_PTHREAD flag makes the library thread-safe, using the POSIX Threads library. Users should pass this flag to the compiler whenever they wish to run multi-threaded code that uses Scythe matrices. Of course, this will only work on systems sporting the pthread libraries. For example:
g++ myprog.cc -DSCYTHE_PTHREAD -pthread
Please note that Scythe matrices are NOT thread-safe when the library is compiled without this flag.
Finally, the SCYTHE_RPACK flag activates some code that makes Scythe play nicely with the R statistical programming environment. R packages that use Scythe should always use this compilation flag, and will generally include a line similar to
PKG_CPPFLAGS = -DSCYTHE_COMPILE_DIRECT -DSCYTHE_RPACK
in the src/Makevars.in file within the package.
Scythe Statistical Library Copyright (C) 2000-2002 Andrew D. Martin and Kevin M. Quinn; 2002-2012 Andrew D. Martin, Kevin M. Quinn, and Daniel Pemstein. All Rights Reserved.
This program is free software; you can redistribute it and/or modify under the terms of the GNU General Public License as published by Free Software Foundation; either version 3 of the License, or (at your option) any later version. See the text files COPYING and LICENSE, distributed with library's source code, for further information.
We gratefully acknowledge support from the United States National Science Foundation (Grants SES-0350646 and SES-0350613), the Department of Political Science, the Weidenbaum Center, and the Center for Empirical Research in the Law at Washington University, and the Department of Government and The Institute for Quantitative Social Science at Harvard University. Neither the foundation, Washington University, nor Harvard University bear any responsibility for this software.
We'd also like to thank the research assistants who have helped us with Scythe: Matthew Fasman, Steve Haptonstahl, Kate Jensen, Laura Keys, Kevin Rompala, Joe Sheehan, and Jean Yang.
1.7.6.1