Evaluating multinomial order restrictions with bridge sampling.

Sarafoglou, Alexandra; Haaf, Julia M.; Ly, Alexander; Gronau, Quentin Frederik; Wagenmakers, Eric‐Jan; Marsman, Maarten

doi:10.1037/met0000411

Cited by 8 publications

(6 citation statements)

References 77 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…x 9 : (0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) ′ x 10 : (1,2,3,4,5,6,7,8,9,9,8,7,6,5,4,3,5,6) ′ x 11 : (1,2,3,4,5,6,7,8,9,9,8,7,6,5,4,4,4, 3) ′ x 12 : (1,2,3,4,5,6,7,8,9,9,8,7,6,5,4,3,6,7) ′ x 13 : (1,2,3,4,5,6,…”

Section: A2 Models With a Higher Number Of Categories 8a21 Methodsmentioning

confidence: 99%

“…Note that all but four teams used the same dependent variable for research question 1 and 2. 8 In the online appendix, we show the included items separately for each team.…”

Section: Variable Inclusionmentioning

confidence: 99%

“…Assuming that every parameter value is equally likely before we see any data, we assign a uniform prior distribution across the parameter vector θ, such that, p(θ | H e ) ∼ Dirichlet(α) with all concentration parameters set to 1. Using the observed frequencies from Haberman (1978), that is, x = (15,11,14,17,5,11,10,4,8,10,7,9,11,3,6,1,1,4) ′ , the Bayes factor comparing the null and encompassing hypotheses is:…”

Section: Bayes Factor Hypothesis Testing Without Inequality Constraintsmentioning

confidence: 99%

See 2 more Smart Citations

[PhD Dissertation] Good Research Practices

Sarafoglou¹

2022

Preprint

View full text Add to dashboard Cite

In this dissertation, I examine research practices and reform ideas aiming to combat the crisis of confidence in psychology (Pashler & Wagenmakers, 2012). I do so through theoretical contributions and empirical work, propose practical guidelines for researchers, and demonstrate how principles of good research can be conveyed to students. The research methods and statistical practices I present facilitate the adherence to the following three principles: (1) respect the empirical cycle; (2) acknowledge uncertainty; and (3) enrich statistical models with theoretical knowledge.

show abstract

Section: A2 Models With a Higher Number Of Categories 8a21 Methodsmentioning

confidence: 99%

“…Note that all but four teams used the same dependent variable for research question 1 and 2. 8 In the online appendix, we show the included items separately for each team.…”

Section: Variable Inclusionmentioning

confidence: 99%

Section: Bayes Factor Hypothesis Testing Without Inequality Constraintsmentioning

confidence: 99%

See 1 more Smart Citation

[PhD Dissertation] Good Research Practices

Sarafoglou¹

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…However, these results would also be consistent with the hypothesis that there is no real difference in terms of risky-choice probabilities beyond being above/below 50% (e.g., André & de Langhe, 2021b). One way to evaluate this hypothesis while sidestepping the challenges associated with order-constrained inference (e.g., Davis-Stober, 2009; Heck & Davis-Stober, 2019; Sarafoglou et al, 2021) is to sample choice probabilities from the posterior distributions and check the proportions that conform to a weaker version of the aforementioned inequalities that omit the 1/2 terms (in red) 12 . The ratio of these proportions is expected to be 1 if choice probabilities are roughly the same across the board (i.e., mirrored opposite patterns are equally likely to be sampled).…”

Section: A Focused Analysis Of Shared Lottery Problemsmentioning

confidence: 99%

Absolute and relative stability of loss aversion across contexts.

Spektor,

Kellen,

Rieskamp

et al. 2024

Journal of Experimental Psychology: General

View full text Add to dashboard Cite

Individuals' decisions under risk tend to be in line with the notion that "losses loom larger than gains." This loss aversion in decision making is commonly understood as a stable individual preference that is manifested across different contexts. The presumed stability and generality, which underlies the prominence of loss aversion in the literature at large, has been recently questioned by studies reporting how loss aversion can disappear, and even reverse, as a function of the choice context. The present study investigated whether loss aversion reflects a trait-like attitude of avoiding losses or rather individuals' adaptability to different contexts. We report three experiments investigating the within-subject context sensitivity of loss aversion in a two-alternative forced-choice task. Our results show that the choice context can shift people's loss aversion, though somewhat inconsistently. Moreover, individual estimates of loss aversion are shown to have a considerable degree of stability. Altogether, these results indicate that even though the absolute value of loss aversion can be affected by external factors such as the choice context, estimates of people's loss aversion still capture the relative dispositions toward gains and losses across individuals. Public Significance StatementLoss aversion is a core feature of prospect theory, and is widely relied upon by researchers and practitioners when characterizing the causes behind real-world phenomena; for example, why people generally dislike stocks despite them having higher returns than risk-free bonds. The present work shows systematic changes in loss aversion across contexts, alongside stable individual differences. These results legitimize the comparison of people's loss aversion relative to one another, while undermining the comparability of estimates to different contexts.

show abstract

“…(e.g., André & de Langhe, 2021b). One way to evaluate this hypothesis while sidestepping the challenges associated with order-constrained inference (e.g., Davis-Stober, 2009;Heck & Davis-Stober, 2019;Sarafoglou et al, 2021) is to sample choice probabilities from the posterior distributions and check the proportions that conform to a weaker version of the aforementioned inequalities that omit the 1 2 terms (in red). 9 The ratio of these proportions is expected to be 1 if choice probabilities are roughly the same across the board (i.e., mirrored opposite patterns are equally likely to be sampled).…”

Section: Tablementioning

confidence: 99%

Absolute and relative stability of loss aversion across contexts

Spektor¹,

Kellen²,

Rieskamp³

et al. 2023

Preprint

View full text Add to dashboard Cite

Individuals’ decisions under risk tend to be in line with the notion that “losses loom larger than gains”. This loss aversion in decision making is commonly understood as a stable individual preference that is manifested across different contexts. The presumed stability and generality, which underlies the prominence of loss aversion in the literature at large, has been recently questioned by studies showing how loss aversion can disappear, and even reverse, as a function of the choice context. The present study investigated whether loss aversion reflects a trait-like attitude of avoiding losses or rather individuals’ adaptability to different contexts. We report three experiments that investigated the within-subject context sensitivity of loss aversion in a two-alternative forced-choice task. The results show beside interindiviudal differences in loss aversion, that the context affects the extent of loss aversion. This indicates that even though the absolute value of loss aversion can be affected by external factors such as the choice context, estimates of people’s loss aversion still capture the relative dispositions towards gains and losses across individuals.

show abstract

Evaluating multinomial order restrictions with bridge sampling.

Cited by 8 publications

References 77 publications

[PhD Dissertation] Good Research Practices

[PhD Dissertation] Good Research Practices

Absolute and relative stability of loss aversion across contexts.

Absolute and relative stability of loss aversion across contexts

Contact Info

Product

Resources

About