<?xml version="1.0"?>
<mods xmlns="http://www.loc.gov/mods/v3" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xs="http://www.w3.org/2001/XMLSchema" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:mods="http://www.loc.gov/mods/v3" version="3.7" xsi:schemaLocation="http://www.loc.gov/mods/v3 http://www.loc.gov/standards/mods/v3/mods-3-7.xsd">
  <titleInfo>
    <title>PERSONALITY SCALE CONSTRUCTION USING LATENT SEMANTIC ANALYSIS AS AN ITEM ANALYSIS METHODOLOGY</title>
  </titleInfo>
  <name>
    <role>
      <roleTerm type="text" authority="marcrelator" authorityURI="http://id.loc.gov/vocabulary/relators" valueURI="http://id.loc.gov/vocabulary/relators/cre">creator</roleTerm>
    </role>
    <namePart>Pollak, Pamela Elizabeth</namePart>
  </name>
  <name>
    <role>
      <roleTerm type="text" authority="marcrelator" authorityURI="http://id.loc.gov/vocabulary/relators" valueURI="http://id.loc.gov/vocabulary/relators/ths">advisor</roleTerm>
    </role>
    <namePart>Mead, Alan</namePart>
  </name>
  <abstract>Linguistics has played an integral role throughout the history of personality scale development. The lexical hypothesis, which implies that by analyzing natural language personality will be understood because all personality is described in language, is the basis for personality scale construction. Despite the important role that language plays in describing personality, psychometric practice has traditionally focused on data analysis, rather than quantitative linguistic analysis when constructing personality scales. This study used a relatively new quantitative linguistics technique, Latent Semantic Analysis (LSA), to construct personality scales. Using an archival sample of N=501 with over n&gt;1000 items, personality scales were constructed to measure aspects of the 16PF Questionnaire and the Big Five model. Scales created using traditional approaches were compared to scales created using LSA in terms of internal consistency reliability, construct validity and convergent validity, predicting five behavioral clusters of self-reported behaviors (e.g., drug-use, undependability, friendliness, creativity and erudition). Results from this study revealed that compared to scales created using a traditional approach, scales constructed using LSA had lower reliabilities, but mostly similar patterns of convergent validity and evidence of substantial construct validity.</abstract>
  <note type="provenance">Submitted by Dana Lamparello (dlampare@iit.edu) on 2012-08-27T20:22:25Z No. of bitstreams: 1 Dissertation _Pamela Pollak (05.07.12).pdf: 1622125 bytes, checksum: 69391e023163c63bf1489049b4fd4e66 (MD5)</note>
  <note type="provenance">Made available in DSpace on 2012-08-27T20:22:25Z (GMT). No. of bitstreams: 1 Dissertation _Pamela Pollak (05.07.12).pdf: 1622125 bytes, checksum: 69391e023163c63bf1489049b4fd4e66 (MD5) Previous issue date: 2012-05</note>
  <note type="thesis">Ph.D. in Psychology, May 2012</note>
  <originInfo>
    <dateCaptured>2012-05-07</dateCaptured>
  </originInfo>
  <originInfo>
    <dateCreated keyDate="yes">2012-05</dateCreated>
  </originInfo>
  <identifier type="hdl">http://hdl.handle.net/10560/2857</identifier>
  <language>
    <languageTerm type="code" authority="rfc3066">en</languageTerm>
  </language>
  <typeOfResource authority="aat" valueURI="http://vocab.getty.edu/page/aat/300028029">Dissertation</typeOfResource>
  <physicalDescription>
    <digitalOrigin>born digital</digitalOrigin>
    <internetMediaType>application/pdf</internetMediaType>
  </physicalDescription>
  <accessCondition type="useAndReproduction" displayLabel="rightsstatements.org">In Copyright</accessCondition>
  <accessCondition type="useAndReproduction" displayLabel="rightsstatements.orgURI">http://rightsstatements.org/page/InC/1.0/</accessCondition>
  <accessCondition type="restrictionOnAccess">Restricted Access</accessCondition>
  <name type="corporate">
    <namePart>PSYCH / Institute of Psychology</namePart>
    <affiliation>Illinois Institute of Technology</affiliation>
    <role>
      <roleTerm type="text">Affiliated department</roleTerm>
    </role>
  </name>
</mods>
