By Beatrice H. Worsley
Communications of the ACM,
Vol. 7 No. 1, Pages 39-44
A comparative study has been made of a variety of numerical techniques for fitting experimental data of the decay type by forms involving the sums of exponentials. Statistical errors of the fitted parameters are also calculated. These methods have been applied to artificially-generated sets of data as well as to the results of experiments with radioactive tracers on both human and animal subjects. Results show that the values of the fitted parameters are very sensitive to variations in the fitting procedure. Therefore great care must be exercised in identifying such values with physical constants. Although the values of functions derived from these fitted parameters which can definitely be associated with physical entities are generally more stable under variations in the fitting techniques, error bounds can be so large that no great confidence can be placed even in them. It would therefore appear best to select a uniform technique both for running the experiments and for analyzing the data, and then to consider as significant only relative results between one subject and the next.
The full text of this article is premium content
No entries found
Log in to Read the Full Article
Please select one of the options below for access to premium content and features.
Create a Web Account
If you are already an ACM member, Communications subscriber, or Digital Library subscriber, please set up a web account to access premium content on this site.
Join the ACM
Become a member to take full advantage of ACM's outstanding computing information resources, networking opportunities, and other benefits.
Subscribe to Communications of the ACM Magazine
Get full access to 50+ years of CACM content and receive the print version of the magazine monthly.
Purchase the Article
Non-members can purchase this article or a copy of the magazine in which it appears.