Aplicação de técnicas estatísticas de reamostragem em hidrologia

This thesis focus on the uncertainty regarding the numerical values of model parameters usually employed in Hydrology. Confidence intervals are adopted in order to consider this uncertainty. Three metodologies are proposed to estimate the standard deviation of these parameters: the Bayesian, the Bootstrap and the Jackknife. Both Bootstrap and Jackknife are called Resampling Methods. The Bootstrap is applied to decide the amount of information needed for modeling the one hundred year flood. It is shown that the resampling techniques are reasonably accurate methods and can be applied to define confidence intervals.

Grantor dc:publisher

Universidade Federal do Rio de Janeiro

Year dc:date.issued

1988

Author dc:creator

• Costa, Fernanda da Serra

Advisor dc:contributor.advisor

• Kelman, Jerson

• Engenharia Civil

Statement dc:rights

• Acesso Aberto

Language dc:language

por

Handle dc:identifier.uri

http://hdl.handle.net/11422/3819

OAI identifier oai:identifier

oai:pantheon.ufrj.br:11422/3819