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

Testing for differentially expressed genes with microarray data.

Chen-An Tsai1, Yi-Ju Chen, James J Chen

  • 1Division of Biometry and Risk Assessment, National Center for Toxicological Research, Food and Drug Administration, Jefferson, AR 72079, USA.

Nucleic Acids Research
|April 25, 2003
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

Investigating the risk of non-alcoholic fatty liver disease in young patients with psoriasis versus non-psoriatic inflammatory skin diseases.

Scientific reports·2026
Same author

Navigating luminal heterogeneity: etiology-based proteogenomic subtyping for targeted treatment strategies in breast cancer.

Molecular cancer·2026
Same author

The Role of Videoconferencing Teleconsultation in Improving Transfer Efficiency and Functional Outcomes in Rural Stroke Care: Retrospective Cohort Study.

JMIR mHealth and uHealth·2026
Same author

Dual-Phase Computed Tomography-Based Deep Learning Architecture for Three-Year Survival Prediction in Hepatocellular Carcinoma.

Journal of imaging informatics in medicine·2026
Same author

Rapid Electrochemical Profiling of Fecal Short-Chain Fatty Acids Using Esterification/Dissociation Fingerprints and Artificial Neural Networks.

Biosensors·2026
Same author

Real-World Safety of JAK Inhibitors in Skin Immune-Mediated Inflammatory Diseases: Boxed Warning Outcomes from a Multinational Cohort Study.

Clinical pharmacology and therapeutics·2026
Same journal

Cap 2'-O-methyltransferase CMTR2 regulates male meiosis independent of its methyltransferase activity.

Nucleic acids research·2026
Same journal

APE1 binds and processes abasic sites present in i-motif DNA and cooperates with PCBP1 in maintenance of telomeric stability.

Nucleic acids research·2026
Same journal

Acquisition of a novel restriction modification system regulates genetic flux and gene expression in the hypervirulent and globally disseminated CC17 lineage of group B Streptococcus.

Nucleic acids research·2026
Same journal

Trans-species microRNAs from the parasitic plant Cuscuta campestris specifically avoid loading onto self Argonautes.

Nucleic acids research·2026
Same journal

Neurochondrin promotes U5 snRNP maturation by regulating AAR2 release from PRPF8.

Nucleic acids research·2026
Same journal

Elongationless start-stop elements are stress-resilient translation gates that are more repressive than uTranslons.

Nucleic acids research·2026
See all related articles

This study compares t-tests and permutation tests for gene expression analysis. Permutation tests are superior for non-normal data with sufficient replicates, while sample design influences test choice.

Area of Science:

  • Bioinformatics
  • Statistical Genetics
  • Computational Biology

Background:

  • Microarray analysis is crucial for understanding gene expression.
  • Accurate statistical methods are needed to detect differential gene expression.
  • Parametric and non-parametric tests offer different approaches to data analysis.

Purpose of the Study:

  • To compare the statistical performance of t-tests and permutation tests for gene expression analysis.
  • To evaluate the impact of data distribution and experimental design on test power and type I error.
  • To provide guidance on selecting appropriate statistical tests for microarray data.

Main Methods:

  • Monte Carlo simulations were employed to assess test performance.
  • One-sample and two-sample t-tests were compared against their permutation test counterparts.

Related Experiment Videos

  • Simulations considered data generated from normal and t-distributions.
  • Analysis included scenarios mimicking two-color dye swap and independent sample designs.

    • Main Results:

    • For normally distributed data, t-tests and permutation tests showed similar performance with adequate replicates.
    • Permutation tests outperformed t-tests for t-distributed data when replicates were at least five.
    • In correlated data (dye swap), one-sample tests were more effective.
    • For independent samples, two-sample tests demonstrated greater power.

    Conclusions:

    • The choice between t-tests and permutation tests depends on data distribution and sample size.
    • Experimental design significantly impacts the power of one-sample versus two-sample tests.
    • Permutation tests offer a robust alternative to t-tests, especially for non-normal microarray data.