Assessing Probabilistic Reasoning in Verbal-Numerical and Graphical-Pictorial Formats: An Evaluation of the Psychometric Properties of an Instrument

Agus, Mirian; Penna, Maria Pietronilla; Peró‐Cebollero, Maribel; Guàrdia‐Olmos, Joan

doi:10.12973/eurasia.2016.1265a

Cited by 8 publications

(4 citation statements)

References 77 publications

(99 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The succeeding sections assessed the basic probabilistic reasoning (in relation to simple and conditional probabilities) in the Numerical and Graphical formats; all items referred to the simple mathematical achievement reached during high school (Agus et al, 2016). This section incorporated five items; these related to the classical problems examined in the literature; specifically, one problem dealt with classical medical diagnoses (for similar problems see, for example Cosmides & Tooby, 1996;Sloman, Over, Slovak, & Stibel, 2003); one was about decks of cards (Tversky & Kahneman, 1974); one was about the outcomes of university examinations (Girotto & Gonzalez, 2001), one was about the roll of dices (Watson & Moritz, 2003); and one was about production defects in a factory (for an example see Appendix; for the questionnaire validation in Italy and Spain refer to (Agus et al, 2016)).…”

Section: Probabilistic Reasoningmentioning

confidence: 99%

See 1 more Smart Citation

What’s about the Calibration between Confidence and Accuracy? Findings in Probabilistic Problems from Italy and Spain

Agus

Peró‐Cebollero

Guàrdia‐Olmos

et al. 2019

EURASIA J MATH SCI T

Self Cite

View full text Add to dashboard Cite

This paper reports some experiments on probabilistic reasoning designed to investigate the impact of the probabilistic problem presentation format (verbalnumerical and graphical-pictorial) on subjects' confidence in the correctness of their performance, other than the calibration between confidence and accuracy. To understand the potential effect of the format, these dimensions were assessed by monitoring contextual and individual variables: time pressure, numerical and visuospatial abilities, statistical anxiety and attitudes towards statistics. The participants included 257 Psychology students without statistical knowledge, recruited from Italian and Spanish universities, who fulfilled self-report validated measures. The students expressed their retrospective judgments of confidence item-by-item in relation to each probabilistic problem. This approach enabled the computation of two measures of calibration (the Bias Index-the Confidence-Judgment Accuracy Quotient). The results indicated that the problem presentation format did not exert a significant main effect on confidence, with the exception of when the interaction between the format and one subscale of the attitudes towards the statistics test was considered. The Bias Index, however, was significantly related to the interaction between format and time pressure. The study offers a point of reflection in relation to the potential effect exerted by the problem format and time constraint in calibration.

show abstract

Section: Probabilistic Reasoningmentioning

confidence: 99%

“…The confidence in the correctness of the response previously provided was assessed using a Likert scale (from 1 = "not confident" to 5 = "completely confident") associated with each item (for an example see the Appendix) (Agus et al, 2016).…”

Section: / 21mentioning

confidence: 99%

What’s about the Calibration between Confidence and Accuracy? Findings in Probabilistic Problems from Italy and Spain

Agus

Peró‐Cebollero

Guàrdia‐Olmos

et al. 2019

EURASIA J MATH SCI T

Self Cite

View full text Add to dashboard Cite

show abstract

“…These findings suggest that the mode of a student's information input preference could play a role in the speed of the information processing and the way in which they interact with the learning materials. However, empirical research related to the link between students' information-input preferences and their cognitive style and ability within the context of probabilistic reasoning suggests that the interactions between these elements of the learning process are complex and plagued by contradictions, which means that making generalisations and devising practical recommendations regarding the most efficient learning strategy is a highly difficult task [10]- [12].…”

Section: Introductionmentioning

confidence: 99%

Are learning preferences really a myth? Exploring the mapping between study approaches and mode of learning preferences

Fitkov-Norris¹,

Yeghiazarian²

2021

ACTA IMEKO

View full text Add to dashboard Cite

This article tested for the presence of the conversion effect in the mapping related to the strength of students’ preferences for receiving information in a visual, auditory, read/write or kinaesthetic modality and the study approaches they adopt when taking notes in class, learning new concepts and revising for exams. The results indicated that the conversion effect is not ubiquitous but is context specific and only present when students seek to learn a new concept and revise for exams. It was present for students with strong visual and read/write preferences but only when attempting to learn a new concept. It was also present for students with a strong auditory preference when revising for exams, while these students preferred to learn a new concept by reading about it. However, the conversion effect did not emerge with kinaesthetic-leaning students in any of the contexts studied, while these students were significantly more likely to utilise auditory input when learning a new concept. Overall, the findings suggest that traditional educational approaches such as lectures and tutorials can be effective in supporting the learning for diverse student groups.

show abstract

“…Por sua vez, Cabrera, Olmos e Costas (1995) observaram que os testes T ERLS e T EGLS melhoraram seus desempenhos em amostras com pelo menos 500 casos. Igualmente, estudos empíricos foram localizados na literatura com as soluções T ERLS (e.g., Pereda, Arch, Peró, Guàrdia, & Forns, 2011) e T ELS (e.g., Agus, Penna, Peró-Cebollero, & Guàrdia-Olmos, 2016).…”

unclassified

Técnicas de correção do teste qui-quadrado para amostras não normais

Silva¹,

Wendt²,

Argimon³

et al. 2018

Aval.Psicol.

View full text Add to dashboard Cite

Este artigo tem o objetivo de avaliar técnicas de correções para o teste Qui-Quadrado (χ 2) aplicadas a modelos da análise fatorial confirmatória (CFA) em amostras não normais. Em uma abordagem simulada e exploratória, foram mensuradas distribuições distintas em termos de curtose multivariada. Na maioria das situações verificadas, observou-se uma tendência dos testes aferidos de realizar correções diferenciadas dos valores do χ 2 , CFI e RMSEA em contextos similares. Como conclusão, dentre outros testes avaliados, sugere-se o uso dos seguintes: teste Elíptico com Mínimos Quadrados Reponderados (Teoria Elíptica); teste da Curtose Heterogênea com Mínimos Quadrados Reponderados (Teoria Curtose Heterogênea) e teste Escalado de Satorra-Bentler com Máxima Verossimilhança (para distribuições com excesso de assimetria e/ou curtose univariadas). Porém, devido ao fator de correção, o teste Escalado de Satorra-Bentler pode aceitar modelos moderadamente mal especificados na presença de extrema curtose. Palavras-chave: teste qui-quadrado; distribuição não normal; análise fatorial confirmatória. ABSTRACT-Techniques for Correction the Chi-Square Test for Non-Normal Samples This paper aims to evaluate techniques for correcting the chi-square test (χ 2) as applied to Confirmatory Factor Analysis (CFA) models in non-normal data. In a simulated and exploratory approach, distinct distributions were analyzed in terms of multivariate kurtosis. In most situations, it was observed a tendency of the analyzed tests to produce differing corrections on the χ 2 values, as well as for the CFI and RMSEA values. Among other tests evaluated, this study suggested the use of the Elliptical Test with Least Squares (Elliptical Theory), Heterogeneous Kurtosis Test with Reweighted Least Squares (Heterogeneous Kurtosis Theory) and Satorra-Bentler Scaled Test with Maximum Likelihood estimation (for distributions with excessive univariate asymmetry and/or kurtosis). However, due to the correction factor, the Satorra-Bentler Scaled test can accept moderately poorly specified models in the presence of extreme kurtosis.

show abstract

Assessing Probabilistic Reasoning in Verbal-Numerical and Graphical-Pictorial Formats: An Evaluation of the Psychometric Properties of an Instrument

Cited by 8 publications

References 77 publications

What’s about the Calibration between Confidence and Accuracy? Findings in Probabilistic Problems from Italy and Spain

What’s about the Calibration between Confidence and Accuracy? Findings in Probabilistic Problems from Italy and Spain

Are learning preferences really a myth? Exploring the mapping between study approaches and mode of learning preferences

Técnicas de correção do teste qui-quadrado para amostras não normais

Contact Info

Product

Resources

About