• About
    • Login
    View Item 
    •   Institutional Repository Home
    • Electronic Theses and Dissertations
    • Electronic Theses and Dissertations
    • View Item
    •   Institutional Repository Home
    • Electronic Theses and Dissertations
    • Electronic Theses and Dissertations
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Browse

    All of Institutional RepositoryCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsDepartmentThis CollectionBy Issue DateAuthorsTitlesSubjectsDepartment

    My Account

    LoginRegister

    On the common but problematic specification of conflated random slopes in multilevel models

    Rights, Jason Douglas
    : https://etd.library.vanderbilt.edu/etd-03192019-223030
    http://hdl.handle.net/1803/15374
    : 2019-03-29

    Abstract

    For multilevel models (MLMs) with fixed slopes, it has been widely recognized that a level-1 variable can have distinct between-cluster and within-cluster fixed effects, and that failing to disaggregate these effects yields a conflated, uninterpretable fixed effect. For MLMs with random slopes, however, I clarify that two different types of slope conflation can occur: that of the fixed component (termed fixed conflation) and that of the random component (termed random conflation). The latter is rarely recognized and not well understood. Here I explain that a model commonly used to disaggregate the fixed component-the contextual effect model with random slopes-troublingly yields a conflated random component. Negative consequences of such random conflation have not been demonstrated. Here I show that they include erroneous interpretation and inferences about the substantively important extent of between-cluster differences in slopes, including either underestimating or overestimating such slope heterogeneity. Furthermore, I show that this random conflation can yield inappropriate standard errors for fixed effects. To aid researchers in practice, I delineate which types of random slope specifications yield an unconflated random component (namely, group-mean-centered models or a proposed unconflated contextual effect model that adds a random component for the cluster mean). I demonstrate the advantages of these unconflated models in terms of estimating and testing random slope variance (i.e., improved power, type I error, and bias) and in terms of standard error estimation for fixed effects (i.e., more accurate standard errors), and make recommendations for which specifications to use for particular research purposes.
    Show full item record

    Files in this item

    Icon
    Name:
    Rights.pdf
    Size:
    1.160Mb
    Format:
    PDF
    View/Open

    This item appears in the following collection(s):

    • Electronic Theses and Dissertations

    Connect with Vanderbilt Libraries

    Your Vanderbilt

    • Alumni
    • Current Students
    • Faculty & Staff
    • International Students
    • Media
    • Parents & Family
    • Prospective Students
    • Researchers
    • Sports Fans
    • Visitors & Neighbors

    Support the Jean and Alexander Heard Libraries

    Support the Library...Give Now

    Gifts to the Libraries support the learning and research needs of the entire Vanderbilt community. Learn more about giving to the Libraries.

    Become a Friend of the Libraries

    Quick Links

    • Hours
    • About
    • Employment
    • Staff Directory
    • Accessibility Services
    • Contact
    • Vanderbilt Home
    • Privacy Policy