A tutorial on testing hypotheses using the Bayes factor.

Hoijtink, Herbert; Mulder, Joris; Lissa, Caspar van; Gu, Xin

doi:10.1037/met0000201

Cited by 174 publications

(225 citation statements)

References 71 publications

Supporting

Mentioning

224

Contrasting

Unclassified

Order By: Relevance

“…After fitting these models, we determined to what extent they explained the observed AECOPD patterns in the two studies by plotting the observed frequencies for each of the 27 patterns against the corresponding predicted frequencies. We also calculated the Bayes Factor to evaluate the amount of support in favour of the unstable versus stable underlying rate models (the lower the Bayes Factor, the higher the support for the "stable underlying rate" model) [17].…”

Section: First Objective: Examining the Presence Of An Underlying Stmentioning

confidence: 99%

Should the number of acute exacerbations in the previous year be used to guide treatments in COPD?

et al. 2020

View full text Add to dashboard Cite

BackgroundIn contemporary management of COPD, the frequent exacerbator phenotype based on a 12-month history of acute exacerbations (AECOPD) is a major determinant of therapeutic recommendations. However, there is considerable debate on the stability of this phenotype over time.MethodsWe used fundamental principles in time-to-event analysis to demonstrate that variation in the frequent exacerbator phenotype has two major sources: variability in the underlying AECOPD rate and the randomness in the occurrence of individual AECOPDs. We re-analysed data from two large cohorts (ECLIPSE and SPIROMICS) using a Bayesian model that separated these sources of variability. We then evaluated the stability of the frequent exacerbator phenotype based on these results.ResultsIn both cohorts, the pattern of AECOPDs strongly supported the presence of an individual-specific underlying AECOPD rate which is stable over time (Bayes Factor <0.001). Despite this, the observed AECOPD rate can markedly vary year-to-year within individual patients. For those with an underlying rate between 0.8–3.1/year, the frequent exacerbator classification, based on the observed rate, changes >30% of the time over two consecutive years due to chance alone. This value increases to >45% for those with an underlying rate between 1.2–2.2/year.ConclusionWhile the underlying AECOPD rate is a stable trait, the frequent exacerbator phenotype based on observed AECOPD patterns is unstable, so much so that its suitability for informing treatment decisions should be questioned. Whether evaluating AECOPD history over longer durations or the use of multivariate prediction models can result in more stable phenotyping needs to be evaluated.

show abstract

Section: First Objective: Examining the Presence Of An Underlying Stmentioning

confidence: 99%

Should the number of acute exacerbations in the previous year be used to guide treatments in COPD?

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The Fisherian and Bayesian approaches both fit this criterion because they condition their inferences on current testing conditions and observed sample characteristics rather than on a long run of equivalent replications (Rubin, 2017, p. 327). I briefly consider Fisher's approach here because there is already a considerable amount of literature covering the Bayesian approach to hypothesis testing (for an introduction, please see Hoijtink et al, 2019), and it is informative to consider how Fisher avoided his own criticism.…”

Section: Discussionmentioning

confidence: 99%

“Repeated sampling from the same population?” A critique of Neyman and Pearson’s responses to Fisher

Rubin

2020

Euro Jnl Phil Sci

View full text Add to dashboard Cite

Fisher (1945a, 1945b, 1955, 1956, 1960) criticised the Neyman-Pearson approach to hypothesis testing by arguing that it relies on the assumption of "repeated sampling from the same population." The present article considers the responses to this criticism provided by Pearson (1947) and Neyman (1977). Pearson interpreted alpha levels in relation to imaginary replications of the original test. This interpretation is appropriate when test users are sure that their replications will be equivalent to one another. However, by definition, scientific researchers do not possess sufficient knowledge about the relevant and irrelevant aspects of their tests and populations to be sure that their replications will be equivalent to one another. Pearson also interpreted the alpha level as a personal rule that guides researchers' behavior during hypothesis testing. However, this interpretation fails to acknowledge that the same researcher may use different alpha levels in different testing situations. Addressing this problem, Neyman proposed that the average alpha level adopted by a particular researcher can be viewed as an indicator of that researcher's typical Type I error rate. Researchers' average alpha levels may be informative from a metascientific perspective. However, they are not useful from a scientific perspective. Scientists are more concerned with the error rates of specific tests of specific hypotheses, rather than the error rates of their colleagues. It is concluded that neither Neyman nor Pearson adequately rebutted Fisher's "repeated sampling" criticism. Fisher's significance testing approach is briefly considered as an alternative to the Neyman-Pearson approach.

show abstract

“…We used Bayesian analyses to quantify the evidence in favor of the hypothesis under consideration. 29 3 | RESULTS…”

Section: Statistical Analysesmentioning

confidence: 99%

Quality of life, social function, emotion, and facial paresis in Dutch vestibular schwannoma patients

Blom

Aarts

Wever

et al. 2020

Laryngoscope Investig Oto

View full text Add to dashboard Cite

Objective(s): The present study aimed to replicate the finding that vestibular schwannoma (VS) patients with facial paresis experience lower health related quality of life (QoL) than those without facial paresis in a Dutch sample, and to extend these findings by measuring VS patients' overall satisfaction with life, social function, and emotion. Methods: Forty-seven VS patients, differing in degree of facial functioning, half of them with and half of them without a facial paresis, answered questionnaires about health related QoL (SF-36 and PANQOL), overall satisfaction with life, fear of being evaluated negatively by others, social avoidance and distress, and characteristics and symptoms of depression. Results: We observed that VS patients with facial paresis experience lower healthrelated QoL as well negatively impacted social function and emotion compared to VS patients without facial paresis. VS patients with facial paresis experienced lower overall satisfaction with life, more characteristic symptoms of depression, and more fear of being evaluated negatively by others than VS patients without facial paresis. Conclusion: These findings corroborate previous research showing an association between impaired facial functioning and lower QoL, but also extend them by showing differences on the quality of social function and emotion. Being aware of this difference between VS patients with and without facial paresis informs health practitioners regarding the specific support these patients might need. Moreover, it is also relevant to consider the influence of a facial paresis on patients' life when deciding between treatment options and in case of surgery the type of resection.

show abstract

A tutorial on testing hypotheses using the Bayes factor.

Cited by 174 publications

References 71 publications

Should the number of acute exacerbations in the previous year be used to guide treatments in COPD?

Should the number of acute exacerbations in the previous year be used to guide treatments in COPD?

“Repeated sampling from the same population?” A critique of Neyman and Pearson’s responses to Fisher

Quality of life, social function, emotion, and facial paresis in Dutch vestibular schwannoma patients

Contact Info

Product

Resources

About