Uncertainty in the Bayesian meta-analysis of normally distributed surrogate endpoints. Bujkiewicz, S., Thompson, J. R, Spata, E., & Abrams, K. R Statistical Methods in Medical Research, 26(5):2287–2318, October, 2017. ![Uncertainty in the Bayesian meta-analysis of normally distributed surrogate endpoints [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex We investigate the effect of the choice of parameterisation of meta-analytic models and related uncertainty on the validation of surrogate endpoints. Different meta-analytical approaches take into account different levels of uncertainty which may impact on the accuracy of the predictions of treatment effect on the target outcome from the treatment effect on a surrogate endpoint obtained from these models. A range of Bayesian as well as frequentist meta-analytical methods are implemented using illustrative examples in relapsing–remitting multiple sclerosis, where the treatment effect on disability worsening is the primary outcome of interest in healthcare evaluation, while the effect on relapse rate is considered as a potential surrogate to the effect on disability progression, and in gastric cancer, where the disease-free survival has been shown to be a good surrogate endpoint to the overall survival. Sensitivity analysis was carried out to assess the impact of distributional assumptions on the predictions. Also, sensitivity to modelling assumptions and performance of the models were investigated by simulation. Although different methods can predict mean true outcome almost equally well, inclusion of uncertainty around all relevant parameters of the model may lead to less certain and hence more conservative predictions. When investigating endpoints as candidate surrogate outcomes, a careful choice of the meta-analytical approach has to be made. Models underestimating the uncertainty of available evidence may lead to overoptimistic predictions which can then have an effect on decisions made based on such predictions.
@article{bujkiewicz_uncertainty_2017-1,
title = {Uncertainty in the {Bayesian} meta-analysis of normally distributed surrogate endpoints},
volume = {26},
issn = {0962-2802, 1477-0334},
url = {http://journals.sagepub.com/doi/10.1177/0962280215597260},
doi = {10.1177/0962280215597260},
abstract = {We investigate the effect of the choice of parameterisation of meta-analytic models and related uncertainty on the validation of surrogate endpoints. Different meta-analytical approaches take into account different levels of uncertainty which may impact on the accuracy of the predictions of treatment effect on the target outcome from the treatment effect on a surrogate endpoint obtained from these models. A range of Bayesian as well as frequentist meta-analytical methods are implemented using illustrative examples in relapsing–remitting multiple sclerosis, where the treatment effect on disability worsening is the primary outcome of interest in healthcare evaluation, while the effect on relapse rate is considered as a potential surrogate to the effect on disability progression, and in gastric cancer, where the disease-free survival has been shown to be a good surrogate endpoint to the overall survival. Sensitivity analysis was carried out to assess the impact of distributional assumptions on the predictions. Also, sensitivity to modelling assumptions and performance of the models were investigated by simulation. Although different methods can predict mean true outcome almost equally well, inclusion of uncertainty around all relevant parameters of the model may lead to less certain and hence more conservative predictions. When investigating endpoints as candidate surrogate outcomes, a careful choice of the meta-analytical approach has to be made. Models underestimating the uncertainty of available evidence may lead to overoptimistic predictions which can then have an effect on decisions made based on such predictions.},
language = {en},
number = {5},
urldate = {2019-05-02},
journal = {Statistical Methods in Medical Research},
author = {Bujkiewicz, Sylwia and Thompson, John R and Spata, Enti and Abrams, Keith R},
month = oct,
year = {2017},
keywords = {Bayes Theorem, Bayesian statistics, Biomarkers, bivariate meta-analysis, Endpoint Determination, Humans, Meta-analysis, Meta-Analysis as Topic, meta-regression, Models, oncology, Recurrence, Statistical, surrogate endpoints, Treatment Outcome, Uncertainty},
pages = {2287--2318},
file = {Bujkiewicz et al. - 2017 - Uncertainty in the Bayesian meta-analysis of norma.pdf:/Users/neil.hawkins/Zotero/storage/UZL2APK8/Bujkiewicz et al. - 2017 - Uncertainty in the Bayesian meta-analysis of norma.pdf:application/pdf},
}
Downloads: 0
{"_id":"WQtWn4SRuCvYaSAri","bibbaseid":"bujkiewicz-thompson-spata-abrams-uncertaintyinthebayesianmetaanalysisofnormallydistributedsurrogateendpoints-2017","authorIDs":[],"author_short":["Bujkiewicz, S.","Thompson, J. R","Spata, E.","Abrams, K. R"],"bibdata":{"bibtype":"article","type":"article","title":"Uncertainty in the Bayesian meta-analysis of normally distributed surrogate endpoints","volume":"26","issn":"0962-2802, 1477-0334","url":"http://journals.sagepub.com/doi/10.1177/0962280215597260","doi":"10.1177/0962280215597260","abstract":"We investigate the effect of the choice of parameterisation of meta-analytic models and related uncertainty on the validation of surrogate endpoints. Different meta-analytical approaches take into account different levels of uncertainty which may impact on the accuracy of the predictions of treatment effect on the target outcome from the treatment effect on a surrogate endpoint obtained from these models. A range of Bayesian as well as frequentist meta-analytical methods are implemented using illustrative examples in relapsing–remitting multiple sclerosis, where the treatment effect on disability worsening is the primary outcome of interest in healthcare evaluation, while the effect on relapse rate is considered as a potential surrogate to the effect on disability progression, and in gastric cancer, where the disease-free survival has been shown to be a good surrogate endpoint to the overall survival. Sensitivity analysis was carried out to assess the impact of distributional assumptions on the predictions. Also, sensitivity to modelling assumptions and performance of the models were investigated by simulation. Although different methods can predict mean true outcome almost equally well, inclusion of uncertainty around all relevant parameters of the model may lead to less certain and hence more conservative predictions. When investigating endpoints as candidate surrogate outcomes, a careful choice of the meta-analytical approach has to be made. Models underestimating the uncertainty of available evidence may lead to overoptimistic predictions which can then have an effect on decisions made based on such predictions.","language":"en","number":"5","urldate":"2019-05-02","journal":"Statistical Methods in Medical Research","author":[{"propositions":[],"lastnames":["Bujkiewicz"],"firstnames":["Sylwia"],"suffixes":[]},{"propositions":[],"lastnames":["Thompson"],"firstnames":["John","R"],"suffixes":[]},{"propositions":[],"lastnames":["Spata"],"firstnames":["Enti"],"suffixes":[]},{"propositions":[],"lastnames":["Abrams"],"firstnames":["Keith","R"],"suffixes":[]}],"month":"October","year":"2017","keywords":"Bayes Theorem, Bayesian statistics, Biomarkers, bivariate meta-analysis, Endpoint Determination, Humans, Meta-analysis, Meta-Analysis as Topic, meta-regression, Models, oncology, Recurrence, Statistical, surrogate endpoints, Treatment Outcome, Uncertainty","pages":"2287–2318","file":"Bujkiewicz et al. - 2017 - Uncertainty in the Bayesian meta-analysis of norma.pdf:/Users/neil.hawkins/Zotero/storage/UZL2APK8/Bujkiewicz et al. - 2017 - Uncertainty in the Bayesian meta-analysis of norma.pdf:application/pdf","bibtex":"@article{bujkiewicz_uncertainty_2017-1,\n\ttitle = {Uncertainty in the {Bayesian} meta-analysis of normally distributed surrogate endpoints},\n\tvolume = {26},\n\tissn = {0962-2802, 1477-0334},\n\turl = {http://journals.sagepub.com/doi/10.1177/0962280215597260},\n\tdoi = {10.1177/0962280215597260},\n\tabstract = {We investigate the effect of the choice of parameterisation of meta-analytic models and related uncertainty on the validation of surrogate endpoints. Different meta-analytical approaches take into account different levels of uncertainty which may impact on the accuracy of the predictions of treatment effect on the target outcome from the treatment effect on a surrogate endpoint obtained from these models. A range of Bayesian as well as frequentist meta-analytical methods are implemented using illustrative examples in relapsing–remitting multiple sclerosis, where the treatment effect on disability worsening is the primary outcome of interest in healthcare evaluation, while the effect on relapse rate is considered as a potential surrogate to the effect on disability progression, and in gastric cancer, where the disease-free survival has been shown to be a good surrogate endpoint to the overall survival. Sensitivity analysis was carried out to assess the impact of distributional assumptions on the predictions. Also, sensitivity to modelling assumptions and performance of the models were investigated by simulation. Although different methods can predict mean true outcome almost equally well, inclusion of uncertainty around all relevant parameters of the model may lead to less certain and hence more conservative predictions. When investigating endpoints as candidate surrogate outcomes, a careful choice of the meta-analytical approach has to be made. Models underestimating the uncertainty of available evidence may lead to overoptimistic predictions which can then have an effect on decisions made based on such predictions.},\n\tlanguage = {en},\n\tnumber = {5},\n\turldate = {2019-05-02},\n\tjournal = {Statistical Methods in Medical Research},\n\tauthor = {Bujkiewicz, Sylwia and Thompson, John R and Spata, Enti and Abrams, Keith R},\n\tmonth = oct,\n\tyear = {2017},\n\tkeywords = {Bayes Theorem, Bayesian statistics, Biomarkers, bivariate meta-analysis, Endpoint Determination, Humans, Meta-analysis, Meta-Analysis as Topic, meta-regression, Models, oncology, Recurrence, Statistical, surrogate endpoints, Treatment Outcome, Uncertainty},\n\tpages = {2287--2318},\n\tfile = {Bujkiewicz et al. - 2017 - Uncertainty in the Bayesian meta-analysis of norma.pdf:/Users/neil.hawkins/Zotero/storage/UZL2APK8/Bujkiewicz et al. - 2017 - Uncertainty in the Bayesian meta-analysis of norma.pdf:application/pdf},\n}\n\n","author_short":["Bujkiewicz, S.","Thompson, J. R","Spata, E.","Abrams, K. R"],"bibbaseid":"bujkiewicz-thompson-spata-abrams-uncertaintyinthebayesianmetaanalysisofnormallydistributedsurrogateendpoints-2017","role":"author","urls":{"Paper":"http://journals.sagepub.com/doi/10.1177/0962280215597260"},"keyword":["Bayes Theorem","Bayesian statistics","Biomarkers","bivariate meta-analysis","Endpoint Determination","Humans","Meta-analysis","Meta-Analysis as Topic","meta-regression","Models","oncology","Recurrence","Statistical","surrogate endpoints","Treatment Outcome","Uncertainty"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/f/FfNE7kWA6pCvwcJZF/myPubs.bib","creationDate":"2019-10-09T17:14:42.792Z","downloads":0,"keywords":["bayes theorem","bayesian statistics","biomarkers","bivariate meta-analysis","endpoint determination","humans","meta-analysis","meta-analysis as topic","meta-regression","models","oncology","recurrence","statistical","surrogate endpoints","treatment outcome","uncertainty"],"search_terms":["uncertainty","bayesian","meta","analysis","normally","distributed","surrogate","endpoints","bujkiewicz","thompson","spata","abrams"],"title":"Uncertainty in the Bayesian meta-analysis of normally distributed surrogate endpoints","year":2017,"dataSources":["usc9shidSEoJgjLwM","ZaHtWavQhcwZqKLNF","iRRNaRs6FkffgErta","zeMwFvgpdRkYAkfoD","v8uQmZsBpiqycmskv"]}