Red X iconGreen tick iconYellow tick icon

    Overview

    The use of regression methods (e.g. linear, logistic, and Poisson regression) for answering scientific questions in the health sciences. Topics include fitting/interpreting regression models and scientific issues in their application (e.g. outcome parameterisation, model selection, missing data).

    This paper builds on the materials of HASC 413, and introduces advanced regression methods for health-related research. Topics include multiple regression for continuous and discrete response variables, model building and diagnostics, control for confounding and interaction.

    About this paper

    Paper title Regression Methods: Health Science Applications
    Subject Health Sciences
    EFTS 0.125
    Points 15 points
    Teaching period Not offered in 2024 (On campus)
    Domestic Tuition Fees ( NZD ) $1,551.63
    International Tuition Fees Tuition Fees for international students are elsewhere on this website.
    Prerequisite
    HASC 413
    Restriction
    PUBH 726, STAT 241, STAT 341
    Limited to
    MHealSc, PGDipHealSc, PGDipSci, MSc
    Notes
    The prerequisite may be waived for students with an equivalent level of knowledge.
    Eligibility

    Suitable for students from any disciplines who are interested in learning advanced regression methods.

    Contact

    Administrator: Amara Boyd - researchstudentadmin-psm@otago.ac.nz

    Teaching staff

    Associate Professor Robin Turner
    Dr Jiaxu Zeng

    Paper Structure
    1. Review of simple linear regression
    2. Multiple regression
    3. Model building and model diagnostics
    4. Introduction to causal inference
    5. Logistic regression
    6. Logistic regression: extension
    7. Poisson regression
    8. Overdispersion and negative binomial models
    9. Model diagnostics for discrete data
    10. Introduction to other types of regression models
    11. Introduction to missing data
    Textbooks

    E. Vittinghoff, D.V. Glidden, S.C. Shiboski, C.E. McCulloch. Regression methods in biostatistics linear, logistic, survival, and repeated measures models. Springer-Verlag, New York (2005).

    Graduate Attributes Emphasised

    Communication, Critical thinking, Research.
    View more information about Otago's graduate attributes.

    Learning Outcomes

    By the end of the course, students are expected to carry out appropriate regression analyses to answer health research questions and gain skills in modelling fitting, model selection and interpretation of results.

    Timetable

    Not offered in 2024

    Location
    Dunedin
    Teaching method
    This paper is taught On Campus
    Learning management system
    Moodle
    Back to top