Bayesian Methods in Practice: Experiences in the Pharmaceutical Industry

Racine, Amy; Grieve, Andrew P.; Flühler, H.; Smith, A. F. M.

doi:10.2307/2347264

Cited by 165 publications

(106 citation statements)

References 48 publications

(22 reference statements)

Supporting

Mentioning

101

Contrasting

Unclassified

Order By: Relevance

“…(1, x 2 ) is considered where x 2 is the log of the dosage in g/ml of a toxin. The data is provided in Table 9 and comes from a real data set analyzed in Racine et al (1986) where m = 4, n(x 1 ) = · · · = n(x 4 ) = 5 and s (x i …”

Section: Tablementioning

confidence: 99%

Goodness of fit for the logistic regression model using relative belief

2017

View full text Add to dashboard Cite

A logistic regression model is a specialized model for product-binomial data. When a proper, noninformative prior is placed on the unrestricted model for the product-binomial model, the hypothesis H 0 of a logistic regression model holding can then be assessed by comparing the concentration of the posterior distribution about H 0 with the concentration of the prior about H 0 . This comparison is effected via a relative belief ratio, a measure of the evidence that H 0 is true, together with a measure of the strength of the evidence that H 0 is either true or false. This gives an effective goodness of fit test for logistic regression.

show abstract

Section: Tablementioning

confidence: 99%

Goodness of fit for the logistic regression model using relative belief

2017

View full text Add to dashboard Cite

show abstract

“…The TSSC also cautioned that individual variation in PK parameters, not just means, matters, see "Bayesian methods in pharmaceutical practice." [21] 2.1 | Lacking from the investigatory accounts As statisticians, we had expected critical examination of the ANSM-approved BIAL/Biotrial protocol including comparison of what was written in the protocol with what was done; an audit-trail of dates for the receipt at BIAL/Biotrial of each cohort's analysed PK and/or PD results; clear documentation of the data (PK and/or PD, adverse events, and external) that were appraised by the BIAL/Biotrial safety committee at each dose-escalation decision-especially the decision to administer 50 mg daily for 10 days when the approved protocol had made no explicit mention of a 50 mg dose; and an unambiguous account (by assigned treatment, volunteer code, and ideally with consent) of the adverse events experienced. In extremis in FIH studies, as here, medical confidentiality should be balanced by the wider public good, as some volunteers and families have demonstrated.…”

Section: Chronology Disclosures and Investigations In Francementioning

confidence: 99%

Statistical issues in first‐in‐human studies on BIA 10‐2474: Neglected comparison of protocol against practice

Bird

Bailey

Grieve

et al. 2017

Pharmaceutical Statistics

View full text Add to dashboard Cite

By setting the regulatory‐approved protocol for a suite of first‐in‐human studies on BIA 10‐2474 against the subsequent French investigations, we highlight 6 key design and statistical issues, which reinforce recommendations by a Royal Statistical Society Working Party, which were made in the aftermath of cytokine release storm in 6 healthy volunteers in the United Kingdom in 2006. The 6 issues are dose determination, availability of pharmacokinetic results, dosing interval, stopping rules, appraisal by safety committee, and clear algorithm required if combining approvals for single and multiple ascending dose studies.

show abstract

“…88-93), who took them from Racine et al (1986). The data comprise two measurements on n = 20 animals.…”

Section: Application To Bioassay Datamentioning

confidence: 99%

A Note on Bayesian Inference After Multiple Imputation

Zhou

Reiter

2010

The American Statistician

View full text Add to dashboard Cite

This article is aimed at practitioners who plan to use Bayesian inference on multiply-imputed datasets in settings where posterior distributions of the parameters of interest are not approximately Gaussian. We seek to steer practitioners away from a naive approach to Bayesian inference, namely estimating the posterior distribution in each completed dataset and averaging functionals of these distributions. We demonstrate that this approach results in unreliable inferences. A better approach is to mix draws from the posterior distributions from each completed dataset, and use the mixed draws to summarize the posterior distribution. Using simulations, we show that for this second approach to work well, the number of imputed datasets should be large. In particular, five to ten imputed datasets-which is the standard recommendation for multiple imputation-is generally not enough to result in reliable Bayesian inferences.

show abstract

Bayesian Methods in Practice: Experiences in the Pharmaceutical Industry

Abstract: SUMMARY Four typical applications of Bayesian methods in pharmaceutical research are outlined. The implications of the use of such methods are discussed, and comparisons with traditional methodologies are given.

Cited by 165 publications

References 48 publications

Goodness of fit for the logistic regression model using relative belief

Goodness of fit for the logistic regression model using relative belief

Statistical issues in first‐in‐human studies on BIA 10‐2474: Neglected comparison of protocol against practice

A Note on Bayesian Inference After Multiple Imputation

Contact Info

Product

Resources

About