Chi-squared and associations in tabular audiology data

Muhammad N. Anwar, Michael P. Oakes, Ken McGarry

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)

Abstract

In this paper, we have used the chi-squared test and Yule's Q measure to discover associations in tables of patient audiology data. These records are examples of heterogeneous medical records, since they contain audiograms, textual notes and typical relational fields. In our first experiment we used the chi-squared measure to discover associations between the different fields of audiology data such as patient gender and patient age with diagnosis. Then, in our second experiment we used Yule's Q to discover the strength and direction of the significant associations found by the chi-squared measure. We then examined two measures of association commonly used in market basket analysis, support and confidence. These did not yield any further associations. We discuss our findings in the context of producing an audiology decision support system.

Original languageEnglish
Title of host publicationProceedings of the World Congress on Engineering 2010 Vol 1
EditorsS. I. Ao, International Association of Engineers
Place of PublicationHong Kong
PublisherNewswood Limited
Pages346-351
Number of pages6
Volume1
ISBN (Print)9789881701299
Publication statusPublished - 1 Dec 2010
Externally publishedYes
EventWorld Congress on Engineering 2010, WCE 2010 - London, United Kingdom
Duration: 30 Jun 20102 Jul 2010

Publication series

NameWCE 2010 - World Congress on Engineering 2010
Volume1

Conference

ConferenceWorld Congress on Engineering 2010, WCE 2010
Country/TerritoryUnited Kingdom
CityLondon
Period30/06/102/07/10

Keywords

  • Audiology
  • Chi-squared
  • Confidence
  • Support
  • Yule's Q

Fingerprint

Dive into the research topics of 'Chi-squared and associations in tabular audiology data'. Together they form a unique fingerprint.

Cite this