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 Concept Videos

McNemar's Test01:23

McNemar's Test

McNemar's Test is a nonparametric statistical test used to determine if there is a significant difference in proportions between two related groups when the outcome is binary (e.g., yes/no, success/failure). It is beneficial when we have paired data, such as pre-test/post-test designs, where the same subjects are measured under two different conditions. The test is named after the statistician Quinn McNemar, who introduced it in 1947. It is commonly used in situations where subjects are...

You might also read

Related Articles

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

Sort by
Same author

Geosmin-producing Species of Coelosphaerium (Synechococcales, Cyanobacteria) in Lake Shinji, Japan.

Scientific reports·2017
Same author

Post-irradiation hypoxic incubation of X-irradiated MOLT-4 cells reduces apoptotic cell death by changing the intracellular redox state and modulating SAPK/JNK pathways.

Apoptosis : an international journal on programmed cell death·2005
Same author

Hypoxia and etanidazole alter radiation-induced apoptosis in HL60 cells but not in MOLT-4 cells.

International journal of radiation biology·2002
Same author

A technique for resection of small bladder tumors using a flexible cystoscope on an outpatient basis: bladder tumor resection with newly designed hot cup forceps.

The Journal of urology·2001
Same author

Signaling by extracellular nucleotides in anterior pituitary cells.

Trends in endocrinology and metabolism: TEM·2001
Same author

Phase Ia study of a hypoxic cell sensitizer doranidazole (PR-350) in combination with conventional radiotherapy.

Anti-cancer drugs·2001

Related Experiment Video

Updated: Jul 7, 2026

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

Neural discriminant analysis.

M Tsujitani1, T Koshimizu

  • 1Department of Engineering Informatics, Faculty of Information Science and Arts, Osaka Electro-Communication University, Osaka 572-8530, Japan. tujitani@isc.osakac.ac.jp

IEEE Transactions on Neural Networks
|February 6, 2008
PubMed
Summary
This summary is machine-generated.

The bootstrap method aids in selecting optimal neural network models for binary data analysis. It improves model selection, goodness-of-fit assessment, and outlier detection in medical diagnostics.

More Related Videos

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations
12:27

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Published on: February 15, 2017

Related Experiment Videos

Last Updated: Jul 7, 2026

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations
12:27

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Published on: February 15, 2017

Area of Science:

  • Statistics
  • Machine Learning
  • Computational Biology

Background:

  • Nonlinear discriminant analysis is crucial for complex datasets.
  • Feedforward neural networks offer powerful modeling capabilities.
  • Statistical model selection and validation are essential for reliable results.

Purpose of the Study:

  • To highlight the utility of the bootstrap method in nonlinear discriminant analysis using feedforward neural networks.
  • To demonstrate the effectiveness of bootstrap-based information criteria for selecting the optimal number of hidden units.
  • To present bootstrap methods for assessing goodness-of-fit, prediction error bias, and residual analysis in neural network models.

Main Methods:

  • Formulating statistical techniques based on the likelihood principle for neural network models with binary responses.
  • Employing bootstrap methods to derive an information criterion for selecting the optimal number of hidden units.
  • Utilizing bootstrapping to summarize goodness-of-fit measures (deviance) and estimate biases in prediction error.
  • Developing bootstrap-based approaches for residual analysis to identify outliers and check distributional assumptions.

Main Results:

  • The bootstrap information criterion is favorable for selecting the optimal number of hidden units in neural network models.
  • Bootstrapping provides reliable estimates for goodness-of-fit and prediction error biases.
  • Bootstrap methods effectively aid in outlier identification and the examination of distributional assumptions through residual analysis.
  • The proposed methods are validated using medical diagnostic data.

Conclusions:

  • The bootstrap method is a valuable tool for enhancing the reliability and interpretability of feedforward neural network models in statistical analysis.
  • Bootstrap-based approaches improve model selection, performance evaluation, and diagnostic checks for neural networks, particularly with binary response data.
  • The application of these methods to medical diagnostic data demonstrates their practical utility in real-world scenarios.