ASA Connect

 View Only

  • 1.  Inclusive gender analyses

    Posted 09-11-2021 19:07
    if we have data on gender, and we use more categories than male, female, how can we analyze these data, beyond descriptively, if (as is often the case) there is a small number in the other categories? Including them in their own categories will usually lead to poor estimation but it doesn't seem right to exclude them either. Does anyone know of any guidelines or have any suggestions?

    ------------------------------
    Melanie Bell, PhD
    Professor of Biostatistics
    Mel & Enid Zuckerman College of Public Health
    Statistics Graduate Interdisciplinary Program
    University of Arizona
    ------------------------------


  • 2.  RE: Inclusive gender analyses

    Posted 09-12-2021 12:15
    Though devoted to race/ethnicity take a look at https://discourse.datamethods.org/t/best-practices-for-recording-race-ethnicity and possibly start a new topic on datamethods.org for sex.

    I don't know of any guidelines.  It's a tough problem.  I think the only high-precision high-power statistical approach is to replace sex with a continuous marker such as a genetic score, hormone level, etc.  Short of that, a Bayesian model that allows the proper amount of information borrowing across 3 or more sex categories is usually the only way to have an adequate sample size.

    ------------------------------
    Frank Harrell
    Department of Biostatistics
    Vanderbilt University School of Medicine
    ------------------------------

    Original Message


  • 3.  RE: Inclusive gender analyses

    Posted 09-14-2021 16:50
    Does Using sex and gender in survey adjustment help?

    Bill

    ------------------------------
    Bill Harris
    Data & Analytics Consultant
    Snohomish County PUD
    ------------------------------

    Original Message


Related Content