Published March 2004 | Version v1
Report

The least squares method formulation with account of systematic errors

Creators

  • 1. International Atomic Energy Agency, Nuclear Data Section, Vienna (Austria)

Description

Use of the Least Squares Method for simultaneous processing of huge data sets is essentially complicated by two mathematic problems - one arises if regression function is not linear in parameters and second is connected with inversion of 'poorly conditioned' covariance matrix of experimental errors in the case when they are correlated. The first problem can be successfully circumvented by the method of discrete optimization of rational approximants and the way to circumvent the second is described in this article

Part of:
Summary report of the second research co-ordination meeting on improvement of the standard cross sections for light elements

Additional details

Publishing Information

Imprint Title
Summary report of the second research co-ordination meeting on improvement of the standard cross sections for light elements
Imprint Pagination
370 p.
Journal Page Range
p. 359-361
Report number
INDC(NDS)--453

Conference

Title
2. research co-ordination meeting on improvement of the standard cross sections for light elements
Dates
13-17 Oct 2003
Place
Gaithersburg, MD (United States)

INIS

Country of Publication
International Atomic Energy Agency (IAEA)
Country of Input or Organization
International Atomic Energy Agency (IAEA)
INIS RN
35095171
Subject category
S99: GENERAL AND MISCELLANEOUS;
Resource subtype / Literary indicator
Conference
Descriptors DEI
ERRORS; FUNCTIONS; LEAST SQUARE FIT; NUCLEAR DATA COLLECTIONS; OPTIMIZATION
Descriptors DEC
MATHEMATICAL SOLUTIONS; MAXIMUM-LIKELIHOOD FIT; NUMERICAL SOLUTION

Optional Information

Notes
2 refs