Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Repositório Instituc...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
versions View all 1 versions
addClaim

This Research product is the result of merged Research products in OpenAIRE.

You have already added 0 works in your ORCID record related to the merged Research product.

Análise estatística da performance de um conjunto de testes auditivos

Authors: Martins, Paula Susana Pereira;

Análise estatística da performance de um conjunto de testes auditivos

Abstract

Este trabalho incidiu na análise estatística da performance do primeiro conjunto de testes de processamento auditivo central adaptados ao português europeu. Os dados em análise resultaram da aplicação desses testes a um conjunto restrito de indivíduos, tendo por objectivo diagnosticar uma patologia específica. Dada a novidade e complexidade do estudo em causa, foi necessário recorrer a métodos estatísticos adequados para avaliar a capacidade de diagnostico dos testes mencionados e caracterizar a forma como o fazem. Este ultimo ponto engloba dois aspectos: a identificação de um conjunto reduzido de testes que contribuem significativamente para efectuar o diagnostico e a construção de um modelo estatístico adequado para classificar novos elementos. A regressão logística foi o método escolhido para resolver este problema, sem prejuízo da aplicação de métodos complementares de análise. Para a amostra em estudo, identificou-se um conjunto de três variáveis, num total de dez, que satisfaz as condições pretendidas. Foram seleccionados dois modelos, um com duas e outros com três das variáveis mais importantes, cuja performance preditiva foi comparada. O primeiro permitiu separar correctamente todos os elementos e revelou melhor performance preditiva, mas evidenciou sobreajuste. No segundo não se verificou este problema, mas os seus resultados são menos satisfatórios tanto na separação como na classificação de elementos. Antes de usar a bateria de testes como meio de diagnostico, recomenda-se a sua aplicação a um conjunto mais vasto de indivíduos.

The present work is about the statistical analysis of the performance of the first central auditory processing test set aimed to European Portuguese. The analyzed data are the outcomes of that test set applied to a small group of persons targeting the diagnosis of a specific pathology. Given the novelty and complexity of this study, adequate statistical methods were demanded to evaluate the diagnosis capability of the aforementioned tests and characterize the way they do it. The later point brings up two distinct aspects: the identification of a small test set that contribute for the diagnostic significantly and the construction of an adequate statistic model useful for new elements classification. Logistic regression was the chosen method to solve this problem, although other complementary analysis methods can be used. For the studied sample, a set of three variables out of ten was identified as satisfying the requested conditions. Two models have been selected, one with two and another with three of the most important variables, to compare their predictive performance. The first one separated correctly every single element and presented better predictive performance, but overfits. In the second one, this problem does not occur, but its results were not so good both separating and classifying elements. Before using the battery of tests for making diagnostics, is recommended to apply it to a broader group of persons.

Mestrado em Matemática e Aplicações

Related Organizations
Keywords

Matemática aplicada, Regressão logística, Audição, Análise estatística

  • BIP!
    Impact byBIP!
    citations
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
citations
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Green