A note on using alpha and stratified alpha to estimate the reliability of a test composed of item parcels

Gordon Rae

    Research output: Contribution to journalArticle

    8 Citations (Scopus)

    Abstract

    Several authors have suggested that prior to conducting a confirmatory factor analysis it may be useful to group items into a smaller number of item `parcels' or `testlets'. The present paper mathematically shows that coefficient alpha based on these parcel scores will only exceed alpha based on the entire set of items if W, the ratio of the average covariance of items between parcels to the average covariance of items within parcels, is greater than unity. If W is less than unity, however, and errors of measurement are uncorrelated, then stratified alpha will be a better lower bound to the reliability of a measure than the other two coefficients. Stratified alpha are also equal to the true reliability of a test when items within parcels are essentially tau-equivalent if one assumes that errors of measurement are not correlated.
    LanguageEnglish
    Pages515-525
    JournalBRITISH JOURNAL OF MATHEMATICAL & STATISTICAL PSYCHOLOGY
    Volume61
    Issue numberPart 2
    DOIs
    Publication statusPublished - Nov 2008

    Fingerprint

    factor analysis
    Group

    Cite this

    @article{f40bb6a2bc284b6d96748fa2585a94db,
    title = "A note on using alpha and stratified alpha to estimate the reliability of a test composed of item parcels",
    abstract = "Several authors have suggested that prior to conducting a confirmatory factor analysis it may be useful to group items into a smaller number of item `parcels' or `testlets'. The present paper mathematically shows that coefficient alpha based on these parcel scores will only exceed alpha based on the entire set of items if W, the ratio of the average covariance of items between parcels to the average covariance of items within parcels, is greater than unity. If W is less than unity, however, and errors of measurement are uncorrelated, then stratified alpha will be a better lower bound to the reliability of a measure than the other two coefficients. Stratified alpha are also equal to the true reliability of a test when items within parcels are essentially tau-equivalent if one assumes that errors of measurement are not correlated.",
    author = "Gordon Rae",
    year = "2008",
    month = "11",
    doi = "10.1348/000711005X72485",
    language = "English",
    volume = "61",
    pages = "515--525",
    journal = "British Journal of Mathematical and Statistical Psychology",
    issn = "0007-1102",
    number = "Part 2",

    }

    A note on using alpha and stratified alpha to estimate the reliability of a test composed of item parcels. / Rae, Gordon.

    In: BRITISH JOURNAL OF MATHEMATICAL & STATISTICAL PSYCHOLOGY, Vol. 61, No. Part 2, 11.2008, p. 515-525.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - A note on using alpha and stratified alpha to estimate the reliability of a test composed of item parcels

    AU - Rae, Gordon

    PY - 2008/11

    Y1 - 2008/11

    N2 - Several authors have suggested that prior to conducting a confirmatory factor analysis it may be useful to group items into a smaller number of item `parcels' or `testlets'. The present paper mathematically shows that coefficient alpha based on these parcel scores will only exceed alpha based on the entire set of items if W, the ratio of the average covariance of items between parcels to the average covariance of items within parcels, is greater than unity. If W is less than unity, however, and errors of measurement are uncorrelated, then stratified alpha will be a better lower bound to the reliability of a measure than the other two coefficients. Stratified alpha are also equal to the true reliability of a test when items within parcels are essentially tau-equivalent if one assumes that errors of measurement are not correlated.

    AB - Several authors have suggested that prior to conducting a confirmatory factor analysis it may be useful to group items into a smaller number of item `parcels' or `testlets'. The present paper mathematically shows that coefficient alpha based on these parcel scores will only exceed alpha based on the entire set of items if W, the ratio of the average covariance of items between parcels to the average covariance of items within parcels, is greater than unity. If W is less than unity, however, and errors of measurement are uncorrelated, then stratified alpha will be a better lower bound to the reliability of a measure than the other two coefficients. Stratified alpha are also equal to the true reliability of a test when items within parcels are essentially tau-equivalent if one assumes that errors of measurement are not correlated.

    U2 - 10.1348/000711005X72485

    DO - 10.1348/000711005X72485

    M3 - Article

    VL - 61

    SP - 515

    EP - 525

    JO - British Journal of Mathematical and Statistical Psychology

    T2 - British Journal of Mathematical and Statistical Psychology

    JF - British Journal of Mathematical and Statistical Psychology

    SN - 0007-1102

    IS - Part 2

    ER -