Integrating clinicians’ opinion in the Bayesian meta-analysis of observational studies: the case of risk factors for falls in community-dwelling older people
<p><strong>Background:</strong> despite the widespread application of Bayesian methods in meta-analysis, the incorporation of clinical informative priors based upon expert opinion is rare.</p><p><strong>Methods:</strong> a questionnaire to elicit beliefs abo...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Milano University Press
2013-10-01
|
| Series: | Epidemiology, Biostatistics and Public Health |
| Online Access: | http://ebph.it/article/view/8909 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850038320085598208 |
|---|---|
| author | Silvia Deandrea Eva Negri Fabrizio Ruggeri |
| author_facet | Silvia Deandrea Eva Negri Fabrizio Ruggeri |
| author_sort | Silvia Deandrea |
| collection | DOAJ |
| description | <p><strong>Background:</strong> despite the widespread application of Bayesian methods in meta-analysis, the incorporation of clinical informative priors based upon expert opinion is rare.</p><p><strong>Methods:</strong> a questionnaire to elicit beliefs about five risk factors for falls in older people was administered to a sample of geriatricians and general practitioners (GPs). The experts were asked to provide a point estimate and upper and lower limits of each relative risk. The elicited opinions were translated into different prior distributions and included in a Bayesian meta-analysis of prospective studies. Frequentist, Bayesian non-informative and fully Bayesian approaches were compared.</p><p><strong>Results:</strong> almost all the clinicians provided the requested information. In most cases, the variability across published studies was greater or similar to that across clinicians. Geriatricians provided more consistent estimates than GPs. When fewer studies were available, the use of the informative prior provided by geriatricians reduced the width of the credibility interval with respect to the frequentist or Bayesian non-informative approaches. Enthusiastic and skeptical priors led to results strongly driven by the prior distribution.</p><p><strong>Conclusions:</strong> this study presents a feasible method for belief elicitation and Bayesian priors’ assessment. The inclusion of external information showed to be useful when only few and/or heterogeneous studies were available from the literature.</p> |
| format | Article |
| id | doaj-art-ae0ed5ff56644074b88220a7e48c028d |
| institution | DOAJ |
| issn | 2282-0930 |
| language | English |
| publishDate | 2013-10-01 |
| publisher | Milano University Press |
| record_format | Article |
| series | Epidemiology, Biostatistics and Public Health |
| spelling | doaj-art-ae0ed5ff56644074b88220a7e48c028d2025-08-20T02:56:37ZengMilano University PressEpidemiology, Biostatistics and Public Health2282-09302013-10-0111110.2427/89098662Integrating clinicians’ opinion in the Bayesian meta-analysis of observational studies: the case of risk factors for falls in community-dwelling older peopleSilvia Deandrea0Eva Negri1Fabrizio Ruggeri2IRCCS - Istituto di Ricerche Farmacologiche 'Mario Negri', Milan, Italy.IRCCS - Istituto di Ricerche Farmacologiche 'Mario Negri', Milan, Italy.Istituto di Matematica Applicata e Tecnologie Informatiche, Consiglio Nazionale delle Ricerche, Milan, Italy.<p><strong>Background:</strong> despite the widespread application of Bayesian methods in meta-analysis, the incorporation of clinical informative priors based upon expert opinion is rare.</p><p><strong>Methods:</strong> a questionnaire to elicit beliefs about five risk factors for falls in older people was administered to a sample of geriatricians and general practitioners (GPs). The experts were asked to provide a point estimate and upper and lower limits of each relative risk. The elicited opinions were translated into different prior distributions and included in a Bayesian meta-analysis of prospective studies. Frequentist, Bayesian non-informative and fully Bayesian approaches were compared.</p><p><strong>Results:</strong> almost all the clinicians provided the requested information. In most cases, the variability across published studies was greater or similar to that across clinicians. Geriatricians provided more consistent estimates than GPs. When fewer studies were available, the use of the informative prior provided by geriatricians reduced the width of the credibility interval with respect to the frequentist or Bayesian non-informative approaches. Enthusiastic and skeptical priors led to results strongly driven by the prior distribution.</p><p><strong>Conclusions:</strong> this study presents a feasible method for belief elicitation and Bayesian priors’ assessment. The inclusion of external information showed to be useful when only few and/or heterogeneous studies were available from the literature.</p>http://ebph.it/article/view/8909 |
| spellingShingle | Silvia Deandrea Eva Negri Fabrizio Ruggeri Integrating clinicians’ opinion in the Bayesian meta-analysis of observational studies: the case of risk factors for falls in community-dwelling older people Epidemiology, Biostatistics and Public Health |
| title | Integrating clinicians’ opinion in the Bayesian meta-analysis of observational studies: the case of risk factors for falls in community-dwelling older people |
| title_full | Integrating clinicians’ opinion in the Bayesian meta-analysis of observational studies: the case of risk factors for falls in community-dwelling older people |
| title_fullStr | Integrating clinicians’ opinion in the Bayesian meta-analysis of observational studies: the case of risk factors for falls in community-dwelling older people |
| title_full_unstemmed | Integrating clinicians’ opinion in the Bayesian meta-analysis of observational studies: the case of risk factors for falls in community-dwelling older people |
| title_short | Integrating clinicians’ opinion in the Bayesian meta-analysis of observational studies: the case of risk factors for falls in community-dwelling older people |
| title_sort | integrating clinicians opinion in the bayesian meta analysis of observational studies the case of risk factors for falls in community dwelling older people |
| url | http://ebph.it/article/view/8909 |
| work_keys_str_mv | AT silviadeandrea integratingcliniciansopinioninthebayesianmetaanalysisofobservationalstudiesthecaseofriskfactorsforfallsincommunitydwellingolderpeople AT evanegri integratingcliniciansopinioninthebayesianmetaanalysisofobservationalstudiesthecaseofriskfactorsforfallsincommunitydwellingolderpeople AT fabrizioruggeri integratingcliniciansopinioninthebayesianmetaanalysisofobservationalstudiesthecaseofriskfactorsforfallsincommunitydwellingolderpeople |