VERIFICAÇÃO DA ADERÊNCIA À LEI DE BENFORD PARA DADOS DE POLUENTES EM RIOS

Felipe Rigos Da Rocha, Raquel Cymrot, André Luiz de Lima Reda, Michael Bruce Beck

Abstract


Confidence on data is essential when analysingthem. Benford states that, in certain numerical samples, thenine numerical digits occur at every given significantposition following a non-uniform probability distribution –namely, a decreasing logarithmic curve. This phenomenon,known in Statistics as an abnormality, may occur undersome specific conditions. That distribution is calledBenford’s law. However, this logarithmic curve does notalways apply on a sample of numerical values directly:sometimes, Benford’s distribution is not followed by thedigits starting from the first one, but rather starting fromsome other. When the basic conditions for Benford’s Law tobe fulfilled are there, but the sample does not follow it, somedata manipulation, or perhaps improper rounding, may beexpected to have occurred in their values. Here, adherenceto Benford’s Law has been searched in series of differentriver pollutant concentrations, as a support forenvironmental control measures.Index Terms ⎯ Benford’s Law, Data quality, Sample bias,Consistency analysis.

Full Text: PDF

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.

----------------------------------------------------------------------

ISSN 2317-3173

----------------------------------------------------------------------

Indexing

Logotipo do IBICT

----------------------------------------------------------------------

Scientific Societies and Directories

Logotipo COPEC Logotipo SHERO Logotipo da Capes

----------------------------------------------------------------------

Follow Us

Logotipo facebook Logotipo LinkedIn Logotipo Twitter