Search program for significant variables
β Scribed by M.J. O'Connell
- Book ID
- 103046875
- Publisher
- Elsevier Science
- Year
- 1974
- Tongue
- English
- Weight
- 532 KB
- Volume
- 8
- Category
- Article
- ISSN
- 0010-4655
No coin nor oath required. For personal study only.
β¦ Synopsis
Title of program: LINCOM pendent variables are converted into significant linear combina-Catalogue number: ABCG tions of the original independent variables. Program obtainable from: CPC Program Library, Queen's Method of solution University ofBelfast, N. Ireland (see application form in this Eigenvalues and eigenvectors of the 'dispersion' matrix for the issue) problem are calculated, and the 'position-vector' of each observation is analysed into the components along the normaliz-Computer: Installation: ed eigenvectors. If the eigenvalues are arranged in decreasing IBM 360/195 RHEL, Chilton order or the linear combination in corresponding order, the ICL 1906A Atlas Laboratory, Chilton most important linear combination is the first and the least CDC6600 CERN important is the last. If some eigenvalues are very small rela-Operating system: IBM/OS with HASP tive to the largest, then the corresponding linear combination may be ignored or set to zero. In this way the complexity of Programming language used: FORTRAN a problem can be reduced. The derivation of momenta from High speed store required: 13K words spark chamber coordinates using this method has been discussed by Wind [1 J, from whose original program the present No. of bits in a word: 32 version has been standardised. Overlay structure: None Typical running time No. of magnetic tapes required: 2 5 seconds on IBM 360/195 (including 2.6 seconds to compile) for analysis of 500 events with 8 independent coordinates. Other peripherals used: Card reader, line-printer Unusual featu res of the program No. of cards in combined program and test deck: 964 Complete data set of observations is not held in core since the Card punching code: EBCDIC dispersion matrix is recomputed after each record is read.
π SIMILAR VOLUMES