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

Probability binning and testing agreement between multivariate immunofluorescence histograms: extending the

K A Baggerly1

  • 1Department of Biostatistics, M. D. Anderson Cancer Center, Houston, Texas 77030-4009, USA. kabagg@mdanderson.org

Cytometry
|October 9, 2001
PubMed
Summary

This study provides a theoretical basis for probability binning, a method for comparing multivariate data distributions in immunohistochemistry. The enhanced method improves sensitivity and flexibility for analyzing complex biological data.

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

Post-hoc analysis of vitamin D status and reduced risk of preterm birth in two vitamin D pregnancy cohorts compared with South Carolina March of Dimes 2009-2011 rates.

The Journal of steroid biochemistry and molecular biology·2015
Same author

Evidence of a role for the novel zinc-finger transcription factor ZKSCAN3 in modulating Cyclin D2 expression in multiple myeloma.

Oncogene·2010
Same author

New tumor markers: CA125 and beyond.

International journal of gynecological cancer : official journal of the International Gynecological Cancer Society·2005
Same author

High-resolution serum proteomic patterns for ovarian cancer detection.

Endocrine-related cancer·2004
Same author

Sensitive and quantitative universal Pyrosequencing methylation analysis of CpG sites.

BioTechniques·2003
Same author

Identifying differentially expressed genes in cDNA microarray experiments.

Journal of computational biology : a journal of computational molecular cell biology·2001

Area of Science:

  • Biostatistics
  • Computational Biology
  • Immunohistochemistry

Background:

  • Assessing significant differences between sample histograms is crucial in immunohistochemistry.
  • The chi-squared test is common for univariate data but struggles with high-dimensional data due to the curse of dimensionality.
  • Data-dependent binning methods, like probability binning, are essential for applying chi-squared tests to multivariate distributions.

Purpose of the Study:

  • To derive the theoretical distribution of the probability binning statistic for a more rigorous foundation.
  • To establish a link between the probability binning statistic and the standard chi-squared statistic.
  • To enhance the probability binning method for improved sensitivity and flexibility in high-dimensional data analysis.

Main Methods:

Related Experiment Videos

  • Derivation of the theoretical distribution for the probability binning statistic.
  • Demonstration that the null distribution is a scaled chi-square.
  • Relating the probability binning statistic to the standard chi-squared statistic.

Main Results:

  • A scaled chi-square distribution was identified as the null distribution for probability binning.
  • Simulations demonstrated that probability binning can be modified for increased sensitivity.
  • Variant statistics were proposed that leverage probability binning's strengths while offering easier application.

Conclusions:

  • Probability binning effectively utilizes adaptive binning to identify patterns in high-dimensional data.
  • The theoretical derivation provides a deeper understanding of the method's behavior.
  • The probability binning method is rendered more flexible and interpretable through its theoretical foundation.