Related Experiment Video
Updated: Sep 6, 2025

A New Technique for Quantitative Analysis of Hair Loss in Mice Using Grayscale Analysis
Published on: March 9, 2015
When might we break the rules? A statistical analysis of aesthetics in photographs
Justin Wang1, Marie A Lee2, Thomas C M Lee1
1Department of Statistics, University of California at Davis, Davis, CA, United States of America.
Abstract:
High-quality photographs often follow certain high-level rules well known to photographers, but some photographs intentionally break these rules. Doing so is usually a matter of artistry and intuition, and the conditions and patterns that allow for rule-breaks are often not well articulated by photographers. This article first applies statistical techniques to help find and evaluate rule-breaking photographs, and then from these photographs discover those patterns that justify their rule-breaking. With this approach, this article discovered some significant patterns that explain why some high-quality photographs successfully break the common photographic rules by positioning the subject in the center or the horizon in the vertical center. These patterns included reflections, leading lines, crossing objects, ambiguous lines, implied lines, thirds line subjects, and busy foregrounds for center horizon photographs, and symmetry, circular-shaped objects, thirds line elements, gestalt, framing, leading lines, and perspective lines for center subject photographs.
Related Concept Videos
Kendall's Tau Test
A τ value...
Statistical Analysis: Overview
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...
Statistical Methods to Analyze Parametric Data: ANOVA
One-way ANOVA is applied when a single independent variable or factor is scrutinized. It compares...
Statistical Significance
Review and Preview
Percentiles are a type of fractile that partition data into...
One-Way ANOVA: Equal Sample Sizes
Different sample means can result in different values for the variance estimate: variance between samples. This is because the variance between samples is calculated as the product of the sample size and the variance between the...

