The bootstrap and the jackknife in ecotoxicology or nonparametric estimates of standard error / by Efraim Halfon. : En13-5/84-47E-PDF

"Laboratory tests for determining chemical and environmental properties of toxic contaminants are time consuming and expensive. Over the years much research has been performed to predict the relation between certain easily measurable properties and others more difficult to obtain. Statistical relations, such as linear regression models, have been developed for this purpose. The problem is, however, that no test has been developed to assure that the predictions of these statistical models are valid also for new chemicals. The bootstrap is a new statistical procedure that allows generalization of the results to chemicals not used in the development of the original model; the bootstrap is used to verify whether a hypothesis developed from a limited data set would be valid, if all possible data would have been available. Thus, the method is very useful to reduce the amount of data to be collected from laboratory experiments to evaluate the toxicity and environmental hazard of toxic contaminants. When the statistical models are used for prediction of new chemical properties, the bootstrap allows an estimate of the probability and range of the chemical property, such as toxicity, bioconcentration, etc."--Exec. summary.

Lien permanent pour cette publication :
publications.gc.ca/pub?id=9.846995&sl=1

• Format MARC XML
• Format MARC HTML

Demander des formats alternatifs