Incorporating Bayesian Ideas into Health-Care Evaluation

Spiegelhalter, David

doi:10.1214/088342304000000080

Cited by 131 publications

(101 citation statements)

References 82 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Further, this variance can be used to produce 'shrunken' (or 'Empirical Bayes') higherlevel residuals which, unlike FE dummy-variable parameter estimates, take account of the unreliability of those estimates; for an application, see Ard and Fairbrother (2017). The degree of "shrinkage" (or exchangeability across level 2 entities) in a RE model is determined from the data, with more shrinkage if there are few observations and/or the estimated variance of the level-2 entities, 2 , is small (see Jones and Bullen 1994;Spiegelhalter 2004).…”

Section: Fixed and Random Effects: Conceptualising The Random Part Ofmentioning

confidence: 99%

Fixed and random effects models: making an informed choice

2018

View full text Add to dashboard Cite

This paper assesses the options available to researchers analysing multilevel (including longitudinal) data, with the aim of supporting good methodological decision-making. Given the confusion in the literature about the key properties of fixed and random effects (FE and RE) models, we present these models' capabilities and limitations. We also discuss the within-between RE model, sometimes misleadingly labelled a 'hybrid' model, showing that it is the most general of the three, with all the strengths of the other two. As such, and because it allows for important extensions-notably random slopes-we argue it should be used (as a starting point at least) in all multilevel analyses. We develop the argument through simulations, evaluating how these models cope with some likely mis-specifications. These simulations reveal that (1) failing to include random slopes can generate anticonservative standard errors, and (2) assuming random intercepts are Normally distributed, when they are not, introduces only modest biases. These results strengthen the case for the use of, and need for, these models.

show abstract

Section: Fixed and Random Effects: Conceptualising The Random Part Ofmentioning

confidence: 99%

Fixed and random effects models: making an informed choice

2018

View full text Add to dashboard Cite

show abstract

“…To construct default priors we followed methods as outlined by others. 117 For the binary outcome of perinatal survival all priors were for log-ORs and were assumed to be normally distributed. The enthusiastic prior was centred at the alternative hypothesis that PLUTO was designed to test.…”

Section: Default Prior Distributionsmentioning

confidence: 99%

“…87,89,117 This is in contrast to the conventional approach to statistics, which, from what is known as a frequentist perspective, provides a deductive approach. There are several important benefits that can be obtained from conducting a Bayesian analysis.…”

Section: Introductionmentioning

confidence: 99%

The Percutaneous shunting in Lower Urinary Tract Obstruction (PLUTO) study and randomised controlled trial: evaluation of the effectiveness, cost-effectiveness and acceptability of percutaneous vesicoamniotic shunting for lower urinary tract obstruction

Morris

Malin²,

Quinlan-Jones³

et al. 2013

Health Technology Assessment

View full text Add to dashboard Cite

“…See, for example, Spiegelhalter, Freedman, and Parmar (1994) and Spiegelhalter (2004). The literature on Bayesian statistical decision theory additionally argues that the purpose of trials is to improve medical decision making and concludes that trials should be designed to maximize subjective expected utility in decision problems of clinical interest.…”

Section: Introductionmentioning

confidence: 99%

Clinical trial design enabling ε-optimal treatment rules

Manski¹,

Tetenov²

2015

View full text Add to dashboard Cite

Medical research has evolved conventions for choosing sample size in randomized clinical trials that rest on the theory of hypothesis testing. Bayesians have argued that trials should be designed to maximize subjective expected utility in settings of clinical interest. This perspective is compelling given a credible prior distribution on treatment response, but Bayesians have struggled to provide guidance on specification of priors. We use the frequentist statistical decision theory of Wald (1950) to study design of trials under ambiguity. We show that ε-optimal rules exist when trials have large enough sample size. An ε-optimal rule has expected welfare within ε of the welfare of the best treatment in every state of nature. Equivalently, it has maximum regret no larger than ε. We consider trials that draw predetermined numbers of subjects at random within groups stratified by covariates and treatments. The principal analytical findings are simple sufficient conditions on sample sizes that ensure existence of ε-optimal treatment rules when outcomes are bounded. These conditions are obtained by application of Hoeffding (1963) large deviations inequalities to evaluate the performance of empirical success rules.

show abstract

Incorporating Bayesian Ideas into Health-Care Evaluation

Cited by 131 publications

References 82 publications

Fixed and random effects models: making an informed choice

Fixed and random effects models: making an informed choice

The Percutaneous shunting in Lower Urinary Tract Obstruction (PLUTO) study and randomised controlled trial: evaluation of the effectiveness, cost-effectiveness and acceptability of percutaneous vesicoamniotic shunting for lower urinary tract obstruction

Clinical trial design enabling ε-optimal treatment rules

Contact Info

Product

Resources

About