Estimating ordinal reliability for Likert-type and ordinal item response data: A conceptual, empirical, and practical guide

Gadermann, Anne M.; Guhn, Martin; Zumbo, Bruno D.

doi:10.7275/n560-j767

Cited by 251 publications

(176 citation statements)

References 31 publications

Supporting

Mentioning

140

Contrasting

Unclassified

Order By: Relevance

“…Otro punto de conflicto en la realización de estudios psicométricos es la fiabilidad, dado que existen distintos coeficientes que permiten estimarla. Entre ellos, por lo general, se encuentran el alfa (Cronbach, 1951), la beta (Revelle, 1979), los omega total, jerárquico y asintótico (McDonald, 1999), el H (Hancock & Mueller, 2001), la theta (Armor, 1973), y el de mayores límites inferiores (greatest lower bound, gbl, Jackson & Agunwamba, 1977), pero el más utilizado históricamente ha sido el coeficiente alfa, y su popularidad se debe, en parte, a su fácil cálculo, su facilidad para comunicar, la posibilidad de calcularlo mediante una sola aplicación de una prueba, y su presencia en distintos softwares estadísticos (Viladrich et al, 2017); incluso, se ha propuesto un alfa para datos ordinales (Oliden & Zumbo, 2008;Zumbo et al, 2007), que se calcula a partir de matrices de correlaciones policóricas con la finalidad de evitar posibles infraestimaciones (Gadermann et al, 2012).…”

Section: El Alfa Y Coeficientes Alternativos Para Estimar La Fiabilidadunclassified

Inventario de Ansiedad de Beck: validez estructural y fiabilidad a través de distintos métodos de estimación en población argentina

Pagan

2021

Acta. Colomb. Psicol.

View full text Add to dashboard Cite

La validez y fiabilidad como propiedades psicométricas consisten en complejos procesos que deben ser revisados constantemente para garantizar la correcta utilización de un instrumento de medición. Por tanto, en el presente estudio se indagó respecto a la validez estructural, la validez factorial y la fiabilidad del Inventario de Ansiedad de Beck (BAI) en su adaptación argentina, a partir de diferentes métodos en una muestra de 746 participantes (Medad = 33.49, DE = 10.55) pertenecientes a la ciudad de Buenos Aires y al conurbano Bonaerense, en Argentina. Específicamente, se realizaron análisis factoriales confirmatorios para probar los modelos de una, dos y cuatro dimensiones, utilizando los métodos de estimación de mínimos cuadrados no ponderados, máxima verosimilitud robusto, mínimos cuadrados ponderados diagonales, y mínimos cuadrados generalizados robusto. Adicional a esto, se indagó respecto a la fiabilidad de la prueba mediante el alfa, omega, glb algebraico y factorial, H, beta, y theta. Los resultados indican que el modelo unidimensional mostró mejores índices de bondad de ajuste independientemente del método de estimación; y que todos los índices de fiabilidad obtenidos fueron aceptables. Esta investigación aporta sólidas evidencias sobre la validez estructural y la fiabilidad del BAI.

show abstract

Section: El Alfa Y Coeficientes Alternativos Para Estimar La Fiabilidadunclassified

Inventario de Ansiedad de Beck: validez estructural y fiabilidad a través de distintos métodos de estimación en población argentina

Pagan

2021

Acta. Colomb. Psicol.

View full text Add to dashboard Cite

show abstract

“…We use a non-parametric test here as the data is on an ordinal scale. We applied a Bonferroni adjustment (.05/3 ¼ .02) to the accepted significance level to account for multiple comparisons (Field, 2013). The HMD-based experience was rated as significantly more interesting (HMD-based…”

Section: Student Appraisal Of the Virtual Counseling Experiencementioning

confidence: 99%

An Evaluation of Virtual Reality Role-Play Experiences for Helping-Profession Courses

Rogers

Hollett

Li³

et al. 2020

Teaching of Psychology

View full text Add to dashboard Cite

Background: Providing students with virtual role-play experiences has the potential to bring counseling role-plays into large undergraduate courses. Objective: The purpose of this study was to trial a virtual reality role-play experience where students played the role of a student counsellor. Method: Seventy-three undergraduate psychology students played the role of a student counsellor interacting with a virtual client in two role-plays, one via desktop and one via head mounted display (HMD). Students provided feedback on their experience. Results: 70% of the students found the experiences very interesting, engaging and immersive, with 82% preferring the HMD mode of presentation. The virtual characters were believable as distressed clients with 96% of students perceiving greater negative than positive emotion expressed by the characters. Most of the students (64%) mood improved from the beginning of the experience to the end, however 14% experienced a decline in mood. The students agreed (95%) that the experiences would be a valuable experience to a psychology course. Conclusion: Our results provide evidence that the virtual role-play experiences are well-liked by students. Teaching Implications: The approach presented in this paper represents a practical method to provide virtual role-play experiences to both on-campus and online undergraduate students.

show abstract

“…Two empirical examples are given. The first example comes from Gadermann et al (2012) who report a dataset where, by using ordinal alpha (α ORD ; Zumbo et al, 2007), another kind of DCER based on replacing the inter-item matrix of PMCs by a matrix of RPCs, the estimate by ρ α was deflated from 0.85 (α ORD ) to 0.46 (ρ α ), that is, 0.39 units of reliability which equals 46% (=0.85-0.46)/0.85).…”

Section: Practical Consequences Of Mechanical Error In the Estimates Of Correlation In Reliabilitymentioning

confidence: 99%

“…A less discussed challenge in the estimates by the traditional estimators of reliability is that their estimates may be radically deflated caused by artificial systematic errors during the estimation or attenuated as a natural consequence of random errors in the measurement (see the discussion of the terms in, e.g., Chan, 2008;Lavrakas, 2008;Gadermann et al, 2012;Revelle and Condon, 2018); deflation and its correction are the foci in this article. Empirical examples discussed later show that, in certain types of datasets, typically with very easy and very difficult tests and tests with incremental difficulty level including both easy and difficult items, the estimates of reliability may be deflated by 0.40-0.60 units of reliability (see, e.g., Zumbo et al, 2007;Gadermann et al, 2012;Metsämuuronen and Ukkola, 2019; see section "Practical Consequences of Mechanical Error in the Estimates of Correlation in Reliability"). Guttman (1945) was the first to show the technical or mechanical underestimation in the estimators of reliability.…”

Section: Introduction: Attenuation and Deflation In The Estimates Of Reliabilitymentioning

confidence: 99%

“…Some options for the latter are proposed by Metsämuuronen (2021c); attenuation corrected PMC and eta. The idea of DCER have been discussed (although not by this name) also, for instance, by Zumbo et al (2007) and Gadermann et al (2012) related to their ordinal alpha and ordinal theta; ordinal alpha and theta uses the matrix of interitem RPCs instead of PMCs in the calculations and those are special cases of DCERs.…”

Section: Introduction: Attenuation and Deflation In The Estimates Of Reliabilitymentioning

confidence: 99%

See 1 more Smart Citation

Deflation-Corrected Estimators of Reliability

Metsämuuronen

2022

Front. Psychol.

View full text Add to dashboard Cite

Underestimation of reliability is discussed from the viewpoint of deflation in estimates of reliability caused by artificial systematic technical or mechanical error in the estimates of correlation (MEC). Most traditional estimators of reliability embed product–moment correlation coefficient (PMC) in the form of item–score correlation (Rit) or principal component or factor loading (λi). PMC is known to be severely affected by several sources of deflation such as the difficulty level of the item and discrepancy of the scales of the variables of interest and, hence, the estimates by Rit and λi are always deflated in the settings related to estimating reliability. As a short-cut to deflation-corrected estimators of reliability, this article suggests a procedure where Rit and λi in the estimators of reliability are replaced by alternative estimators of correlation that are less deflated. These estimators are called deflation-corrected estimators of correlation (DCER). Several families of DCERs are proposed and their behavior is studied by using polychoric correlation coefficient, Goodman–Kruskal gamma, and Somers delta as examples of MEC-corrected coefficients of correlation.

show abstract

Estimating ordinal reliability for Likert-type and ordinal item response data: A conceptual, empirical, and practical guide

Cited by 251 publications

References 31 publications

Inventario de Ansiedad de Beck: validez estructural y fiabilidad a través de distintos métodos de estimación en población argentina

Inventario de Ansiedad de Beck: validez estructural y fiabilidad a través de distintos métodos de estimación en población argentina

An Evaluation of Virtual Reality Role-Play Experiences for Helping-Profession Courses

Deflation-Corrected Estimators of Reliability

Contact Info

Product

Resources

About