Resolving the 50‐year debate around using and misusing Likert scales

By James Carifio, Rocco J. Perla. Medical Education, 2008

1,043 citations recorded by the source corpus.

Subfields: Family Practice, Physiology, Public Health, Environmental and Occupational Health

View Paper: https://www.semanticscholar.org/paper/7e9863e98c8b5852da894d82f31b90a68e60cc89

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Family Practice

In Physiology

In Public Health, Environmental and Occupational Health

Citations in the corpus

Five-Point Likert Items: t test versus Mann-Whitney-Wilcoxon ( Addendum added October 2012 ) (2010, methodology): “There exists disagreement amongst scholars about whether Likert data should be analyzed with parametric statistics such as the t test or nonparametric statistics such as the rank-based Mann-Whitney-Wilcoxon (MWW) (Carifio & Perla, 2008; Jamieson, 2004).”
Corporate social responsibility in cruising: Using materiality analysis to create shared value (2016, methodology): “The study analysed Likert scale items as intervallevel data (Carifio and Perla, 2008).”
Five-Point Likert Items: t test versus Mann-Whitney-Wilcoxon (2010, methodology): “There exists disagreement amongst scholars about whether Likert data should be analyzed with parametric statistics such as the t test or nonparametric statistics such as the rank-based Mann-Whitney-Wilcoxon (MWW) (Carifio & Perla, 2008; Jamieson, 2004).”
Crowd-sourcing NLG Data: Pictures Elicit Better Data. (2016, methodology): “…however, was justified repeatedly by (Carifio and Perla, 2008), (Norman, 2010) and more recently by (Murray, 2013) as a “perfectly appropriate” (Carifio and Perla, 2008) statistical method for Likert scales that may be used by researchers “with no fear of coming to the wrong conclusion”…”
Recruiting Participants With Programming Skills: A Comparison of Four Crowdsourcing Platforms and a CS Student Mailing List (2022, methodology): “We treated the Likert data as an interval variable [7] and ran t-tests on them, which is common practice in the CHI community [29].”
The use of rating and Likert scales in Natural Language Generation human evaluation tasks: A review and some recommendations (2019, methodology): “In particular, it can be controversial whether rating and Likert scales should be considered as ordinal or interval scales; see for example Knapp (1990), Jamieson (2004), Pell (2005), Cariﬁo et al. (2008), Norman (2010) and Sullivan and Artino (2013).”
Evidence-Based Survey Design: The Use of a Midpoint on the Likert Scale (2017, methodology): “Thus, it is “perfectly appropriate to summarise the ratings generated from Likert scales using means and standard deviations, and it is perfectly appropriate to use parametric techniques like Analysis of Variance to analyse Likert scales” (Carifio & Perla, 2008, p. 1151).”
Likert scales, levels of measurement and the “laws” of statistics (2010, methodology): “expounded by Carifio and Perla (2008) in their response to Jamieson (2004). They begin, as I have, in pointing out that those who defend the logical position that parametric methods cannot be used on ordinal data ignore the many studies of robustness.”
Likert Data: What to Use, Parametric or Non-Parametric? (2013, neutral): “The controversy begins with the type of analysis to use – parametric or non-parametric?Carifio and Perla, Resolving the 50-year debate around using and misusing Likert scales (2008) believe the issue of whether a parametric test or non-parametric one is suited to the analysis of Likert scale data st”