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

Introduction to Statistics01:17

Introduction to Statistics

59.5K
The science of statistics involves collecting, analyzing, interpreting, and presenting data. The method of collecting, organizing, and summarizing data is called descriptive statistics. The systematic method of drawing inferences from the sample data and predicting unknown characteristics of a population is called inferential statistics.
In statistics, the collection of individuals or objects under study is called population. The idea of sampling is to select a portion of the larger population...
59.5K
Statistical Analysis: Overview01:11

Statistical Analysis: Overview

12.9K
When we take repeated measurements on the same or replicated samples, we will observe inconsistencies in the magnitude. These inconsistencies are called errors. To categorize and characterize these results and their errors, the researcher can use statistical analysis to determine the quality of the measurements and/or suitability of the methods.
One of the most commonly used statistical quantifiers is the mean, which is the ratio between the sum of the numerical values of all results and the...
12.9K
Statistical Inference Techniques in Hypothesis Testing: Parametric Versus Nonparametric Data01:16

Statistical Inference Techniques in Hypothesis Testing: Parametric Versus Nonparametric Data

346
Statistical inference techniques, paramount in hypothesis testing, differentiate into two broad categories: parametric and nonparametric statistics.
Parametric statistics, as the name suggests, assumes that data follow a specific distribution, often a normal distribution. This assumption enables robust hypothesis testing and estimation. Parametric methods, like the Student's t-test or Goodness-of-fit test, are frequently employed in biostatistics due to their robustness. For instance,...
346
Statistical Hypothesis Testing01:16

Statistical Hypothesis Testing

5.1K
Hypothesis testing is a critical statistical procedure facilitating informed, evidence-based decisions. It begins with a hypothesis, which is a tentative explanation, or a prediction about a population parameter. This hypothesis can be either a null hypothesis (H0), indicating no effect or difference, or an alternative hypothesis (Ha), suggesting an effect or difference.
Statistical significance measures the probability that an observed result occurred by chance. If this probability, known as...
5.1K
How Data are Classified: Categorical Data01:11

How Data are Classified: Categorical Data

40.3K
A variable, usually notated by capital letters such as X and Y, is a characteristic or measurement that can be determined for each member of a population. Data are the actual values of variables. They may be numbers, or they may be words. Datum is a single value.
Data are classified based on whether they are measurable or not. Categorical data cannot be measured; instead, it can be divided into categories. For example, if Y denotes a person's party affiliation, some examples of Y include...
40.3K
Data: Types and Distribution01:19

Data: Types and Distribution

1.2K
In biostatistics, data are the observations collected for analysis. There are two main types: parametric and non-parametric. Parametric data, which include continuous (e.g., weight) and discrete numerical data (e.g., number of tablets), assume a particular distribution pattern, often the normal distribution. Non-parametric data do not adhere to a specific distribution and typically comprise nominal (e.g., gender) and ordinal categorical data (e.g., pain scale ratings).
Distributions in...
1.2K

You might also read

Related Articles

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

Sort by
Same author

Exploring neural manifolds across a wide range of intrinsic dimensions.

PLoS computational biology·2026
Same author

Artificial Intelligence-Based Automated Analysis for Pleural Effusion Detection on Thoracic Ultrasound: A Systematic Review.

Diagnostics (Basel, Switzerland)·2026
Same author

K-operator for Modelling Neurodegeneration: Simulations, fMRI Application, Eigenvalue Analysis and Recurrence Plots.

Journal of medical systems·2025
Same author

A High-Order Cumulant Extension of Quasi-Linkage Equilibrium.

ArXiv·2025
Same author

Intercostal Artery Screening with Color Doppler Thoracic Ultrasound in Pleural Procedures: A Potential Yet Underexplored Imaging Modality for Minimizing Iatrogenic Bleeding Risk in Interventional Pulmonology.

Journal of clinical medicine·2025
Same author

Thoracic Ultrasound for Pre-Procedural Dynamic Assessment of Non-Expandable Lung: A Non-Invasive, Real-Time and Multifaceted Diagnostic Tool.

Journal of clinical medicine·2025

Related Experiment Video

Updated: Dec 5, 2025

Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques
08:05

Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques

Published on: June 30, 2020

7.9K

Statistical learning theory of structured data.

Mauro Pastore1, Pietro Rotondo1, Vittorio Erba1

  • 1Dipartimento di Fisica, Università degli Studi di Milano and INFN, Via Celoria 16, I-20133 Milan, Italy.

Physical Review. E
|October 20, 2020
PubMed
Summary

Statistical physics models for data with structure, like object manifolds, improve supervised learning. This research bridges physics and learning theory, revealing nonmonotonic entropy and a transition indicating low generalization error.

More Related Videos

Eye-tracking Technology and Data-mining Techniques used for a Behavioral Analysis of Adults engaged in Learning Processes
10:43

Eye-tracking Technology and Data-mining Techniques used for a Behavioral Analysis of Adults engaged in Learning Processes

Published on: June 10, 2021

5.7K
A Psychophysics Paradigm for the Collection and Analysis of Similarity Judgments
08:12

A Psychophysics Paradigm for the Collection and Analysis of Similarity Judgments

Published on: March 1, 2022

2.8K

Related Experiment Videos

Last Updated: Dec 5, 2025

Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques
08:05

Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques

Published on: June 30, 2020

7.9K
Eye-tracking Technology and Data-mining Techniques used for a Behavioral Analysis of Adults engaged in Learning Processes
10:43

Eye-tracking Technology and Data-mining Techniques used for a Behavioral Analysis of Adults engaged in Learning Processes

Published on: June 10, 2021

5.7K
A Psychophysics Paradigm for the Collection and Analysis of Similarity Judgments
08:12

A Psychophysics Paradigm for the Collection and Analysis of Similarity Judgments

Published on: March 1, 2022

2.8K

Area of Science:

  • Statistical Physics
  • Machine Learning Theory
  • Statistical Learning Theory

Background:

  • Traditional statistical physics for supervised learning uses unrealistic data models (independent variables).
  • Recent work explores structured data, such as points on object manifolds.
  • Existing statistical learning theory struggles to explain deep learning's generalization.

Purpose of the Study:

  • To bridge recent physics research on structured data with statistical learning theory.
  • To explain deep learning's generalization properties by integrating physical data models.
  • To compute Vapnik-Chervonenkis entropy for structured data using physics methods.

Main Methods:

  • Integration of physical data models into statistical learning theory.
  • Application of combinatorial and statistical mechanics methods.
  • Computation of Vapnik-Chervonenkis entropy for kernel machines and structured data (k-dimensional simplexes, spherical manifolds).

Main Results:

  • Computed Vapnik-Chervonenkis entropy for structured data, showing nonmonotonic behavior with sample size.
  • Observed a transition beyond storage capacity, proposed as a proxy for nonmonotonicity and low generalization error.
  • Identified a vanishing synaptic volume at the transition, quantifying the impact of data structure.

Conclusions:

  • Structured data, unlike unstructured data, exhibits nonmonotonic entropy, challenging traditional bounds.
  • The identified transition serves as a key indicator of good generalization performance.
  • Replica theory can quantify data structure's impact, especially for margin learning.