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

Group sequential designs for phase II trials with historical controls.

M N Chang1, J J Shuster, J L Kepner

  • 1Department of Statistics, University of Florida, Gainesville 32601-3330, USA.

Controlled Clinical Trials
|August 10, 1999
PubMed
Summary

This study introduces novel two-step statistical tests for comparing experimental and control groups using historical data. These methods efficiently detect differences in means for normal distributions and dichotomous data, allowing for early conclusions.

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

Effect of Lonicera japonica extract on lactation performance, antioxidant status, and endocrine and immune function in heat-stressed mid-lactation dairy cows.

Journal of dairy science·2020
Same author

Effects of different types of zinc supplement on the growth, incidence of diarrhea, immune function, and rectal microbiota of newborn dairy calves.

Journal of dairy science·2020
Same author

Infectious diseases in dogs rescued during dogfighting investigations.

Veterinary journal (London, England : 1997)·2016
Same author

Packed red blood cell transfusion is not associated with increased risk of necrotizing enterocolitis in premature infants.

Journal of perinatology : official journal of the California Perinatal Association·2014
Same author

Phase 1 trial of dichloroacetate (DCA) in adults with recurrent malignant brain tumors.

Investigational new drugs·2013
Same author

Design and statistical analysis of oral medicine studies: common pitfalls.

Oral diseases·2009

Area of Science:

  • Statistics
  • Biostatistics
  • Experimental Design

Background:

  • Traditional statistical tests often require concurrent control groups, increasing costs and time.
  • Historical control data offers a valuable alternative for comparative studies.
  • Assessing differences between experimental and control populations is crucial in research.

Purpose of the Study:

  • To develop and present novel two-step statistical tests.
  • To enable the detection of different means using historical control data.
  • To extend these tests for both normally distributed and dichotomous data.

Main Methods:

  • The proposed methods utilize historical control data for comparison.
  • Two-step hypothesis testing procedures are employed.

Related Experiment Videos

  • The tests accommodate normally distributed data with known, possibly different, variances.
  • The methodology is extended to handle dichotomous outcome data.

    • Main Results:

    • The two-step tests effectively detect differences in population means.
    • The methods are applicable to both continuous (normal) and categorical (dichotomous) data.
    • The framework allows for early acceptance or rejection of hypotheses.

    Conclusions:

    • The proposed two-step tests provide an efficient approach for comparative studies using historical controls.
    • These statistical methods offer flexibility for various data types.
    • Early decision-making is facilitated, potentially saving resources.