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

Evaluating data from behavioral analysis: visual inspection or statistical models?

G S. Fisch1

  • 1Department of Epidemiology and Public Health and the Child Study Center, Division of Biostatistics, Yale University, 60 College Street, 06520, New Haven, CT, USA

Behavioural Processes
|May 23, 2001
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 journal

Sex and brain maturation underlie the attribution of incentive salience to conditioned stimuli in Wistar rats.

Behavioural processes·2026
Same journal

Shining a light on jellyfish behaviour: Enhanced motor activity and positive phototaxis in Aurelia coerulea.

Behavioural processes·2026
Same journal

Detour-task performance in color polymorphic male mosquitofish.

Behavioural processes·2026
Same journal

Behavioral and physiological changes during the estrous cycle of socially housed female guinea pigs.

Behavioural processes·2026
Same journal

Flexible time-series analysis: A dynamically aware method for inferring directed dependencies in behavioral data.

Behavioural processes·2026
Same journal

Effects of group size and landmarks on escape behavior of three fish species.

Behavioural processes·2026
See all related articles

Visual inspection of behavioral data can misinterpret trends, leading to inaccurate treatment effect identification. Statistical methods can improve the analysis of repeated measures data, augmenting traditional visual inspection.

Area of Science:

  • Behavioral Science
  • Applied Behavior Analysis
  • Quantitative Psychology

Background:

  • Traditional behavior analysis predominantly uses single-subject designs and visual data inspection.
  • Historically, inferential statistics have been resisted in behavior analysis despite known limitations of visual inspection.
  • Limitations of visual inspection include misinterpreting trends and identifying level shifts in autocorrelated data.

Purpose of the Study:

  • To evaluate the efficacy of experimental manipulations in behavior analysis.
  • To investigate the accuracy of visual inspection in identifying treatment effects, particularly with autocorrelated data.
  • To introduce and evaluate statistical procedures to enhance the analysis of behavioral data.

Main Methods:

  • Conducted a series of experiments using traditional behavior analysis data.

Related Experiment Videos

  • Examined the ability of trained behavior analysts to detect level shifts and trends in modestly autocorrelated data.
  • Presented and discussed nonparametric and other statistical techniques for analyzing repeated measures data.

    • Main Results:

    • Trained behavior analysts frequently misidentified or missed trends in autocorrelated data, mistaking them for level shifts or treatment effects.
    • Visual inspection alone is insufficient for accurate analysis of behavioral data with autocorrelation.
    • Advanced statistical methods offer more sophisticated approaches to analyzing repeated measures data.

    Conclusions:

    • Visual inspection of behavioral data has significant limitations, especially with autocorrelated data.
    • Statistical inferential procedures can effectively augment, not replace, visual inspection in behavior analysis.
    • The integration of statistical techniques can improve the reliability and validity of behavioral data analysis.