To be Direct or not: Reversing Likert Response Format Items

García-Fernández, Jaime; Postigo, Álvaro; Izquierdo, Marcelino Cuesta; González-Nuevo, Covadonga; Menéndez-Aller, Álvaro; Cueto, Eduardo García

doi:10.1017/sjp.2022.20

Cited by 8 publications

(4 citation statements)

References 31 publications

(45 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The decision to remove the negative items had direct support from previous studies with the AWS, in which a short version was developed excluding these items [46] and the method effect produced by them [47]. Indirectly, it was also supported by the consistent methodological literature which has shown the deterioration effects of a measurement model when items in opposite directions are used (reversed or negatively worded items relative to the construct) [61,74,75].…”

Section: Discussionmentioning

confidence: 89%

Psychometric Validity of the Areas of Work Life Scale (AWS) in Teachers and Healthcare Workers in México

García

Merino-Soto

García-Rivas³

2023

EJIHPE

View full text Add to dashboard Cite

The areas of work life scale (AWS) has shown to be a suitable marker of perceived fit between employees’ abilities and the psychosocial demands of the job, but validation studies are practically nonexistent in the Latino population. The purpose of this study was twofold: firstly, to examine the factor structure, reliability, and invariance between sex and occupation of the AWS scale, and secondly, to test the AWS–burnout relationship within the framework of the structural mediational model proposed by Leiter and Maslach (2005). N = 305 health workers and N = 324 teachers from different work settings answered the AWS and MBI-GS scales. In this study, 64.4% of the participants were females (N = 405), and the mean age was 34.7 (sd = 11.7, rank = 56). Robust methods for statistical analyses were used. The results showed that the original version had marginal fit indices due to a method effect (negative phrasing items), and when seven negative items were removed, a final best model was found (CFI = 0.997; RMSEA = 0.060; SRMRu = 0.047). Non-invariance between occupation and sex was found, and the internal consistency was from marginal to satisfactory (ω = 0.658 to 0.840). The mediational structural model tested confirmed the expected associations between AWS and burnout. In conclusion, the Mexican translation of the AWS in its 22-reduced version showed reliability and validity in Mexican work contexts, specifically in healthcare workers and teachers.

show abstract

Section: Discussionmentioning

confidence: 89%

Psychometric Validity of the Areas of Work Life Scale (AWS) in Teachers and Healthcare Workers in México

García

Merino-Soto

García-Rivas³

2023

EJIHPE

View full text Add to dashboard Cite

show abstract

“…This feature was also present in data from the four reverse-worded items on the C scale (Items 3, 6, 9, and 11; see Section 3 of the Supplementary Material ). It is not clear whether this is saying something about the (in)convenience of using reverse-worded items alongside other items that are not reverse-worded, but this outcome certainly adds fuel to the controversy over the use of reverse wording (see, for example, García-Fernández et al, 2022 ; Józsa & Morgan, 2017 ; Kam, 2023 ; Suárez-Álvarez et al, 2018 ; Swain et al, 2008 ; Vigil-Colet et al, 2020 ).…”

Section: Resultsmentioning

confidence: 99%

Are the Steps on Likert Scales Equidistant? Responses on Visual Analog Scales Allow Estimating Their Distances

García‐Pérez

2023

Educational and Psychological Measurement

View full text Add to dashboard Cite

A recurring question regarding Likert items is whether the discrete steps that this response format allows represent constant increments along the underlying continuum. This question appears unsolvable because Likert responses carry no direct information to this effect. Yet, any item administered in Likert format can identically be administered with a continuous response format such as a visual analog scale (VAS) in which respondents mark a position along a continuous line. Then, the operating characteristics of the item would manifest under both VAS and Likert formats, although perhaps differently as captured by the continuous response model (CRM) and the graded response model (GRM) in item response theory. This article shows that CRM and GRM item parameters hold a formal relation that is mediated by the form in which the continuous dimension is partitioned into intervals to render the discrete Likert responses. Then, CRM and GRM characterizations of the items in a test administered with VAS and Likert formats allow estimating the boundaries of the partition that renders Likert responses for each item and, thus, the distance between consecutive steps. The validity of this approach is first documented via simulation studies. Subsequently, the same approach is used on public data from three personality scales with 12, eight, and six items, respectively. The results indicate the expected correspondence between VAS and Likert responses and reveal unequal distances between successive pairs of Likert steps that also vary greatly across items. Implications for the scoring of Likert items are discussed.

show abstract

“…It is also important to examine the wording of different items. Our findings support the suggestion of other studies [57,62,109] to eliminate the use of negatively worded items that is based on a false assumption that they are measuring the same thing as the positively worded items. At minimum, we encourage scale developers not to add negations to question stems as this can complicate how respondents interpret the item and lead to misunderstandings.…”

Section: Discussionmentioning

confidence: 99%

Psychometric evaluation of the Trust in Science and Scientists Scale

Wolff,

Breakwell,

Wright

2024

R. Soc. Open Sci.

View full text Add to dashboard Cite

Reliable and valid measurement of trust in science and scientists is important. Assessing levels of such trust is important in determining attitudes and predicting behaviours in response to medical and scientific interventions targeted at managing public crises. However, trust is a complex phenomenon that has to be understood in relation to both distrust and mistrust. The Trust in Science and Scientists Scale has been adopted with increasing frequency in large-scale public health research. Detailed psychometric evaluation of the scale is overdue and makes meaningful comparisons between studies that use the scale difficult. Here, we examine the scale’s dimensionality across five separate samples. We find that two factors emerge that are divided by their item polarity. Implications for scale use and trust in science measurement are discussed.

show abstract

To be Direct or not: Reversing Likert Response Format Items

Cited by 8 publications

References 31 publications

Psychometric Validity of the Areas of Work Life Scale (AWS) in Teachers and Healthcare Workers in México

Psychometric Validity of the Areas of Work Life Scale (AWS) in Teachers and Healthcare Workers in México

Are the Steps on Likert Scales Equidistant? Responses on Visual Analog Scales Allow Estimating Their Distances

Psychometric evaluation of the Trust in Science and Scientists Scale

Contact Info

Product

Resources

About