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

Are flexible designs sound?

Carl-Fredrik Burman1, Christian Sonesson

  • 1AstraZeneca R & D, SE-431 83 Mölndal, Sweden. carl-fredrik.burman@astrazeneca.com

Biometrics
|September 21, 2006
PubMed
Summary
This summary is machine-generated.

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

Bayesian Solutions for Assessing Differential Effects in Biomarker Positive and Negative Subgroups.

Pharmaceutical statistics·2024
Same author

Digital twins and Bayesian dynamic borrowing: Two recent approaches for incorporating historical control data.

Pharmaceutical statistics·2024
Same author

The MaxCombo Test Severely Violates the Type I Error Rate.

JAMA oncology·2023
Same author

On model-based time trend adjustments in platform trials with non-concurrent controls.

BMC medical research methodology·2022
Same author

A framework for assessing the impact of accelerated approval.

PloS one·2022
Same author

Estimands and Complex Innovative Designs.

Clinical pharmacology and therapeutics·2022
Same journal

Fast penalized generalized estimating equations for large longitudinal functional datasets.

Biometrics·2026
Same journal

Causally-interpretable random-effects meta-analysis.

Biometrics·2026
Same journal

Statistical inference for mean function of partially observed functional time series.

Biometrics·2026
Same journal

Subgroup identification via Interaction Tree and Mixed Model for Repeated Measures with application to Alzheimer's disease.

Biometrics·2026
Same journal

Finite mixtures of linear quantile regressions with concomitant variables: a solution to endogeneity in longitudinal data modeling.

Biometrics·2026
Same journal

Discussion on "INTACT: a method for integration of longitudinal physical activity data from multiple sources" by Jingru Zhang, Erjia Cui, Hongzhe Li, and Haochang Shou.

Biometrics·2026
See all related articles

Flexible experimental designs, while allowing modifications, can lead to invalid statistical inferences. A standard approach using weighted tests may violate basic principles, necessitating alternative methods for valid hypothesis testing.

Area of Science:

  • Biostatistics
  • Experimental Design
  • Statistical Inference

Background:

  • Flexible experimental designs permit substantial modifications during studies.
  • Sample size adjustments based on interim data or external information are key features.
  • Standard flexible methodologies often employ weighted tests to control Type I error rates.

Purpose of the Study:

  • To evaluate the validity of standard flexible experimental designs and their associated weighted tests.
  • To identify potential violations of fundamental statistical inference principles.
  • To explore alternative hypothesis testing methods for flexible designs.

Main Methods:

  • Analysis of a standard flexible design methodology combined with a weighted test.
  • Examination of statistical inference principles using independent normal observations.

Related Experiment Videos

  • Illustrative example demonstrating rejection of the null hypothesis despite negative sample average.

    • Main Results:

    • The standard flexible design methodology with weighted testing was found to violate basic inference principles.
    • An example demonstrated a scenario where the null hypothesis (mu <= 0) was rejected, yet the observed data average was negative.
    • This indicates a fundamental issue with the general form of flexible design and its associated weighted test.

    Conclusions:

    • Flexible designs, in their most general form with standard weighted tests, are not statistically valid.
    • The observed violations challenge the integrity of inferences drawn from such methods.
    • Further research into alternative hypothesis tests is required to ensure the validity of flexible experimental designs.