Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Common multiple comparison procedures.

K B Gerald

    Nurse Anesthesia
    |September 1, 1990
    PubMed
    Summary

    Choosing the best multiple comparison test depends on balancing statistical power and conservatism. The Student-Newman-Keuls (SNK) procedure offers a practical compromise for researchers.

    Related Concept Videos

    You might also read

    Related Articles

    Articles linked to this work by shared authors, journal, and citation graph.

    Sort by
    Same author

    Brain cancer and leukemia and exposure to power-frequency (50- to 60-Hz) electric and magnetic fields.

    Epidemiologic reviews·1997
    Same author

    Determination of power and sample size for a statistical test.

    Nurse anesthesia·1991
    Same author

    Nonparametric statistical methods.

    Nurse anesthesia·1991
    Same author

    Statistical analysis of categorical data.

    Nurse anesthesia·1991
    Same author

    Linear regression and correlation.

    Nurse anesthesia·1990
    Same author

    Analysis of bladder carcinoma by subsite. Cystoscopic location may have prognostic value.

    Cancer·1990

    Area of Science:

    • Statistics
    • Biostatistics
    • Experimental Design

    Background:

    • Multiple comparison tests are crucial for analyzing data with multiple groups.
    • Selecting the appropriate test impacts the reliability of detecting true differences.
    • Various methods exist, each with different levels of conservatism and statistical power.

    Purpose of the Study:

    • To evaluate and compare different multiple comparison procedures.
    • To provide guidance on selecting the most suitable test based on research goals.
    • To discuss the trade-offs between statistical power and conservatism in hypothesis testing.

    Main Methods:

    • Review and comparison of common multiple comparison tests (e.g., LSD, Duncan's, Scheff's S, Tukey's, SNK).
    • Analysis of test characteristics regarding Type I error rates (conservatism) and power.
    • Discussion of decision rules for test selection, including the Waller and Duncan k ratio rule.

    Main Results:

    • Nonconservative tests like Fisher's LSD and Duncan's offer high power but increase the risk of false positives.
    • Highly conservative tests, such as Scheff's S, are less prone to false positives but may lack power for pairwise comparisons.
    • The Student-Newman-Keuls (SNK) procedure is frequently employed as a practical balance between conservatism and power.

    Conclusions:

    • The optimal multiple comparison test is context-dependent, balancing the need for conservatism against the desire for statistical power.
    • The SNK procedure represents a commonly accepted compromise in many research applications.
    • Researchers should carefully consider their objectives regarding Type I error control when selecting a statistical test.

    Related Experiment Videos