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

The effect of missing data on estimating a respondent's location using ratings data.

R J De Ayala1

  • 1Department of Educational Psychology, University of Nebraska-Lincoln, Lincoln, NE 68588-0345, USA. rdeayala2@unl.edu

Journal of Applied Measurement
|April 18, 2003
PubMed
Summary

This study examined methods for handling missing data in Likert scale responses. The hot-decking procedure proved most effective in mitigating the impact of omitted responses on person location estimates.

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

A Comparative Evaluation of Kernel Equating and Test Characteristic Curve Equating.

Applied psychological measurement·2018
Same author

An introduction to mixture item response theory models.

Journal of school psychology·2017
Same author

The Assessment of Dimensionality for Use in Item Response Theory.

Multivariate behavioral research·2016
Same author

A Validation and Reliability Study of the Physical Activity and Healthy Food Efficacy Scale for Children (PAHFE).

Health education & behavior : the official publication of the Society for Public Health Education·2007
Same author

Estimating person locations from partial credit data containing missing responses.

Journal of applied measurement·2006

Area of Science:

  • Social Science Research
  • Psychometrics
  • Survey Methodology

Background:

  • Rating scales like the Likert scale are common in social science.
  • Missing data in response vectors can arise for various reasons.
  • Respondent location estimates can be affected by omitted responses.

Purpose of the Study:

  • To investigate the impact of omitted responses on person location estimates.
  • To evaluate four different missing data handling strategies.
  • To identify the most effective method for mitigating the effects of omissions.

Main Methods:

  • A Monte Carlo simulation study was conducted.
  • Four methods were compared: ignoring omissions, using midpoint imputation, hot-decking, and a likelihood-based approach.

Related Experiment Videos

  • The study assessed the effect of varying omission levels on location estimates.

    • Main Results:

    • The hot-decking procedure demonstrated superior performance compared to other methods.
    • The effectiveness of each method varied with the level of missing data.
    • Omitted responses significantly impacted person location estimates.

    Conclusions:

    • Hot-decking is a recommended strategy for handling omitted responses in Likert scale data.
    • Practitioners should consider appropriate missing data techniques to ensure accurate person location estimation.
    • Further research may explore other imputation methods.