last modified: 21-NOV-1985 | catalog | categories | new | search |

NESC9804 BRGLM.

BRGLM, Interactive Linear Regression Analysis by Least Square Fit

top ]
1. NAME OR DESIGNATION OF PROGRAM:  BRGLM.
top ]
2. COMPUTERS
To submit a request, click below on the link of the version you wish to order. Only liaison officers are authorised to submit online requests. Rules for requesters are available here.
Program name Package id Status Status date
BRGLM NESC9804/01 Tested 21-NOV-1985

Machines used:

Package ID Orig. computer Test computer
NESC9804/01 DEC VAX 11/780 DEC VAX 11/780
top ]
3. DESCRIPTION OF PROGRAM OR FUNCTION

BRGLM is an interactive program written to fit general linear regression models by least squares and to provide a variety of statistical diagnostic information about the fit. Stepwise and all-subsets regression can be carried out also. There are facilities for interactive data management (e.g. setting missing value flags, data transformations) and tools for constructing design matrices for the more commonly-used models such  as factorials, cubic splines, and autoregressions.
top ]
4. METHOD OF SOLUTION

The least squares computations are based on the orthogonal (QR) decomposition of the design matrix obtained using the modified Gram-Schmidt algorithm.
top ]
5. RESTRICTIONS ON THE COMPLEXITY OF THE PROBLEM

The current release  of BRGLM allows maxima of 1000 observations, 99 variables, and 3000  words of main memory workspace. For a problem with N observations and P variables, the number of words of main memory storage required is MAX(N*(P+6), N*P+P*P+3*N, and 3*P*P+6*N). Any linear model may be fit although the in-memory workspace will have to be increased for larger problems.
top ]
6. TYPICAL RUNNING TIME

Computation time is generally small compared  to interactive data transmission rates and timesharing delays. A model with 30 observations and 11 variables requires about 2 CP seconds to execute on a DEC VAX11/780.
NESC9804/01
NEA-DB has run the test case included in this package on a VAX-11/780. Compilation and linking of all modules required 3.34 seconds of CPU time. Since execution was performed interactively, no CPU times were available.
top ]
7. UNUSUAL FEATURES OF THE PROGRAM:
top ]
8. RELATED AND AUXILIARY PROGRAMS:
top ]
9. STATUS
Package ID Status date Status
NESC9804/01 21-NOV-1985 Tested at NEADB
top ]
10. REFERENCES:
NESC9804/01, included references:
- J.T. Ringland AND R.E. Bohrer:
  Users Manual for BRGLM:
  Interactive General Linear Model Regression Version 3
  SAND84-8226  (August 1984)
top ]
11. MACHINE REQUIREMENTS

170K bytes. Six disk files are addressed for  data input and output and for temporary storage.
top ]
12. PROGRAMMING LANGUAGE(S) USED
Package ID Computer language
NESC9804/01 FORTRAN-77
top ]
13. OPERATING SYSTEM UNDER WHICH PROGRAM IS EXECUTED:
NESC9804/01
VAX/VMS.
top ]
14. OTHER PROGRAMMING OR OPERATING INFORMATION OR RESTRICTIONS

It should be relatively straighforward to implement BRGLM on older Fortran compilers by removing Fortran 77 OPEN statements and converting CHARACTER declarations to INTEGER.
top ]
15. NAME AND ESTABLISHMENT OF AUTHORS

SNLL    J.T. Ringland*

UICS    R.E. Bohrer

CALB    M.E. Sherman

         Sandia National Laboratories
         P.O. Box 969
         Livermore, California 94550

* Contact
top ]
16. MATERIAL AVAILABLE
NESC9804/01
File name File description Records
NESC9804_01.001 information file 61
NESC9804_01.002 BRGLM driver source program 580
NESC9804_01.003 basic utility routines 1647
NESC9804_01.004 procedure 2 subroutines 471
NESC9804_01.005 procedure 3 subroutines 2879
NESC9804_01.006 procedure 4 subroutines 208
NESC9804_01.007 procedure 5 subroutines 171
NESC9804_01.008 procedure 6 subroutines 3200
NESC9804_01.009 procedure 7 subroutines 793
NESC9804_01.010 procedure 8 subroutines 1109
NESC9804_01.011 procedure 9 subroutines 109
NESC9804_01.012 command procedure for program implementation 18
NESC9804_01.013 test case input data 35
NESC9804_01.014 test case printed output 295
NESC9804_01.015 program report 4712
top ]
17. CATEGORIES
  • P. General Mathematical and Computing System Routines

Keywords: interactive computing, least square fit, regression analysis, spline functions, statistics.