Bayesian Cost-Effectiveness Analysis of Medical Treatments

 
 
Chapman and Hall (Verlag)
  • erschienen am 30. Januar 2019
  • |
  • 300 Seiten
 
E-Book | ePUB mit Adobe DRM | Systemvoraussetzungen
978-1-351-74436-2 (ISBN)
 
Cost-effectiveness analysis is becoming an increasingly important tool for decision making in the health systems. Cost-Effectiveness of Medical Treatments formulates the cost-effectiveness analysis as a statistical decision problem, identifies the sources of uncertainty of the problem, and gives an overview of the frequentist and Bayesian statistical approaches for decision making. Basic notions on decision theory such as space of decisions, space of nature, utility function of a decision and optimal decisions, are explained in detail using easy to read mathematics.FeaturesFocuses on cost-effectiveness analysis as a statistical decision problem and applies the well-established optimal statistical decision methodology.Discusses utility functions for cost-effectiveness analysis.Enlarges the class of models typically used in cost-effectiveness analysis with the incorporation of linear models to account for covariates of the patients. This permits the formulation of the group (or subgroup) theory.Provides Bayesian procedures to account for model uncertainty in variable selection for linear models and in clustering for models for heterogeneous data. Model uncertainty in cost-effectiveness analysis has not been considered in the literature. Illustrates examples with real data.In order to facilitate the practical implementation of real datasets, provides the codes in Mathematica for the proposed methodology. The motivation for the book is to make the achievements in cost-effectiveness analysis accessible to health providers, who need to make optimal decisions, to the practitioners and to the students of health sciences. Elas Moreno is Professor of Statistics and Operational Research at the University of Granada, Spain, Corresponding Member of the Royal Academy of Sciences of Spain, and elect member of ISI. Francisco Jos Vzquez-Polo is Professor of Mathematics and Bayesian Methods at the University of Las Palmas de Gran Canaria, and Head of the Department of Quantitative Methods. Miguel ngel Negrn is Senior Lecturer in the Department of Quantitative Methods at the ULPGC. His main research topics are Bayesian methods applied to Health Economics, economic evaluation and cost-effectiveness analysis, meta-analysis and equity in the provision of healthcare services.
  • Englisch
  • London
  • |
  • Großbritannien
Taylor & Francis Ltd
  • Für höhere Schule und Studium
  • |
  • Für Beruf und Forschung
60 schwarz-weiße Abbildungen
978-1-351-74436-2 (9781351744362)
Elias Moreno is Professor of Statistics and Operational Research at the University of Granada, Spain, Corresponding Member of the Royal Academy of Sciences of Spain, and elect member of ISI. He served as a President of the Spanish Statistical and Operational Research Society, 1992-1996, and Head of the Department of Statistics and Operational Research, 1986-1990, and he is in the editorial board of RACSAM, Test, ESTADISTICA and Global & Local Economic Review. He is co-editor of Bayesian Robustness, Vol. 29, Institute of Mathematical Statistics, Bayesian Statistics 6, Oxford University Press, and Topics on Methodological and Applied Statistical Inference, Springer-Verlag. He published around 120 papers on Statistical Inference in Statistical Journal including Journal of the Royal Statistical Society Series B, Journal of the American Statistical Association, The Annals of Statistics, Statistical Science, European Journal of Operational Research and Statistical Methods in Medical Research. Francisco Jose Vazquez-Polo is Professor of Mathematics and Bayesian Methods at the University of Las Palmas de Gran Canaria, and Head of the Department of Quantitative Method. He published twelve chapters of books and around 70 papers in Economics Journals including Journal of Business Economics & Statistics, European Journal of Health Economics, Health Economics, Journal of Health Economics, and in Statistical Journals including Journal of the Royal Statistical Society (Series B, C & D), European Journal of Operational Research, Computational Statistics and Data Analysis, Statistics in Medicine and Statistical Methods in Medical Research. Miguel Angel Negrin is Senior Lecturer in the Department of Quantitative Methods at the ULPGC. His main research topics are Bayesian methods applied to Health Economics, economic evaluation and cost-effectiveness analysis, meta-analysis and equity in the provision of healthcare services. Part of his research has been published in Journals of reference in Health Economics and Statistics, such as Health Economics, Journal of Health Economics, European Journal of Health Economics, Value in Health, Statistics in Medicine, Medical Decision Making, European Journal of Operational Research and Statistical Methods in Medical Research. He serves in the editorial board of Gaceta Sanitaria (IF 2017: 1,58).
Elias Moreno is Professor of Statistics and Operational Research at the University of Granada, Spain, Corresponding Member of the Royal Academy of Sciences of Spain, and elect member of ISI. He served as a President of the Spanish Statistical and Operational Research Society, 1992-1996, and Head of the Department of Statistics and Operational Research, 1986-1990, and he is in the editorial board of RACSAM, Test, ESTADISTICA and Global & Local Economic Review. He is co-editor of Bayesian Robustness, Vol. 29, Institute of Mathematical Statistics, Bayesian Statistics 6, Oxford University Press, and Topics on Methodological and Applied Statistical Inference, Springer-Verlag. He published around 120 papers on Statistical Inference in Statistical Journal including Journal of the Royal Statistical Society Series B, Journal of the American Statistical Association, The Annals of Statistics, Statistical Science, European Journal of Operational Research and Statistical Methods in Medical Research. Francisco Jose Vazquez-Polo is Professor of Mathematics and Bayesian Methods at the University of Las Palmas de Gran Canaria, and Head of the Department of Quantitative Method. He published twelve chapters of books and around 70 papers in Economics Journals including Journal of Business Economics & Statistics, European Journal of Health Economics, Health Economics, Journal of Health Economics, and in Statistical Journals including Journal of the Royal Statistical Society (Series B, C & D), European Journal of Operational Research, Computational Statistics and Data Analysis, Statistics in Medicine and Statistical Methods in Medical Research. Miguel Angel Negrin is Senior Lecturer in the Department of Quantitative Methods at the ULPGC. His main research topics are Bayesian methods applied to Health Economics, economic evaluation and cost-effectiveness analysis, meta-analysis and equity in the provision of healthcare services. Part of his research has been published in Journals of reference in Health Economics and Statistics, such as Health Economics, Journal of Health Economics, European Journal of Health Economics, Value in Health, Statistics in Medicine, Medical Decision Making, European Journal of Operational Research and Statistical Methods in Medical Research. He serves in the editorial board of Gaceta Sanitaria (IF 2017: 1,58).
<ol><li><b>
</b></li><li><b>Health economics evaluation </b></li><li>

<b>Introduction </b>


<b>Conventional types of economic evaluation </b>


<b>The variables of cost-effectiveness analysis </b>


<b>Sources of uncertainty in cost-effectiveness analysis </b>


<b>Conventional tools for cost-effectiveness analysis </b>


<b>The incremental cost-effectiveness ratio </b>


<b>The incremental net benefit </b>


<b>Cost-effectiveness acceptability curve </b>


<b>Conventional subgroup analysis </b>


<b>An outline of Bayesian cost-effectiveness analysis </b>

<b><b>
</b></b>



</li><li><b><b>Statistical inference in parametric models </b></b></li><li>


<b><b>Introduction </b></b>


<b><b>Parametric sampling models </b></b>


<b><b>The likelihood function </b></b>


<b><b>Likelihood sets </b></b>


<b><b>The maximum likelihood estimator </b></b>


<b><b>Proving consistency and asymptotic normality </b></b>


<b><b>Reparametrization to a subparameter </b></b>


<b><b>Parametric Bayesian models </b></b>


<b><b>Subjective priors </b></b>


<b><b>Conjugate priors </b></b>


<b><b>Objective priors </b></b>


<b><b>The predictive distribution </b></b>


<b><b>Bayesian model selection </b></b>


<b><b>Intrinsic priors for model selection </b></b>


<b><b>The normal linear model </b></b>


<b><b>Maximum likelihood estimators </b></b>


<b><b>Bayesian estimators </b></b>


<b><b>An outline of variable selection </b></b>


<b><b><b>
</b></b></b>


</li><li><b><b><b>Statistical decision theory </b></b></b></li><li>


<b><b><b>Introduction </b></b></b>


<b><b><b>Elements of a decision problem </b></b></b>


<b><b><b>Ordering rewards </b></b></b>


<b><b><b>Lotteries </b></b></b>


<b><b><b>The Utility function </b></b></b>


<b><b><b>Axioms for the existence of the utility function </b></b></b>


<b><b><b>Criticisms to the utility function </b></b></b>


<b><b><b>Lotteries that depend on a parameter </b></b></b>


<b><b><b>The minimax strategy </b></b></b>


<b><b><b>The Bayesian strategy </b></b></b>


<b><b><b>Comparison </b></b></b>


<b><b><b>Optimal decisions in the presence of sampling information</b></b></b>


<b><b><b>The frequentist procedure </b></b></b>


<b><b><b>The Bayesian procedure </b></b></b>


<b><b><b><b>
</b></b></b></b>


</li><li><b><b><b><b>Cost-effectiveness analysis. Optimal treatments </b></b></b></b></li><li>


<b><b><b><b>Introduction </b></b></b></b>


<b><b><b><b>The net benefit of a treatment </b></b></b></b>


<b><b><b><b>Utility functions of the net benefit </b></b></b></b>


<b><b><b><b>The utility function U Optimal treatments </b></b></b></b>


<b><b><b><b>Interpretation of the expected utility </b></b></b></b>


<b><b><b><b>The utility function U Optimal treatments </b></b></b></b>


<b><b><b><b>Interpretation of the expected utility </b></b></b></b>


<b><b><b><b>Penalizing a new treatment </b></b></b></b>


<b><b><b><b>Parametric classes of probabilistic rewards </b></b></b></b>


<b><b><b><b>Frequentist predictive distribution of the net bene</b></b></b></b>


<b><b><b><b>Bayesian predictive distribution of the net benefit </b></b></b></b>


<b><b><b><b>Statistical models for cost and effectiveness </b></b></b></b>


<b><b><b><b>The normal-normal model </b></b></b></b>


<b><b><b><b>The lognormal-normal model </b></b></b></b>


<b><b><b><b>The lognormal-Bernoulli model </b></b></b></b>


<b><b><b><b>The bivariate normal model </b></b></b></b>


<b><b><b><b>The dependent lognormal-Bernoulli model </b></b></b></b>


<b><b><b><b>A case study </b></b></b></b>


<b><b><b><b>The cost-effectiveness acceptability curve for the utility</b></b></b></b>


<b><b><b><b>function U </b></b></b></b>


<b><b><b><b>The case of completely unknown rewards </b></b></b></b>


<b><b><b><b>The case of parametric rewards </b></b></b></b>


<b><b><b><b>The cost-effectiveness acceptability curve for the utility</b></b></b></b>


<b><b><b><b>function U </b></b></b></b>


<b><b><b><b>Comments on cost-effectiveness acceptability curve </b></b></b></b>


<b><b><b><b><b>
</b></b></b></b></b>


</li><li><b><b><b><b><b>Cost-effectiveness analysis for heterogenous data </b></b></b></b></b></li><li>


<b><b><b><b><b>Introduction </b></b></b></b></b>


<b><b><b><b><b>Clustering </b></b></b></b></b>


<b><b><b><b><b>Prior distributions </b></b></b></b></b>


<b><b><b><b><b>Posterior distribution of the cluster models </b></b></b></b></b>


<b><b><b><b><b>Examples </b></b></b></b></b>


<b><b><b><b><b>Bayesian meta-analysis </b></b></b></b></b>


<b><b><b><b><b>The Bayesian meta-model </b></b></b></b></b>


<b><b><b><b><b>The likelihood of the meta-parameter and the</b></b></b></b></b>


<b><b><b><b><b>linking distribution </b></b></b></b></b>


<b><b><b><b><b>Properties of the linking distribution </b></b></b></b></b>


<b><b><b><b><b>Examples </b></b></b></b></b>


<b><b><b><b><b>Contents</b></b></b></b></b>


<b><b><b><b><b>The predictive distribution of (c; e) conditional on a partition</b></b></b></b></b>


<b><b><b><b><b>The unconditional predictive distribution of (c; e) </b></b></b></b></b>


<b><b><b><b><b>The predictive distribution of the net benefit z </b></b></b></b></b>


<b><b><b><b><b>The case of independent c and e </b></b></b></b></b>


<b><b><b><b><b>Optimal treatments </b></b></b></b></b>


<b><b><b><b><b>Examples </b></b></b></b></b>


<b><b><b><b><b><b>
</b></b></b></b></b></b>


</li><li><b><b><b><b><b><b>Subgroup cost-effectiveness</b> <b>analysis </b></b></b></b></b></b></li><li>

</li></ol>

<b><b><b><b><b><b>Introduction </b></b></b></b></b></b>


<b><b><b><b><b><b>The data and the Bayesian model </b></b></b></b></b></b>


<b><b><b><b><b><b>The independent normal-normal model </b></b></b></b></b></b>


<b><b><b><b><b><b>The normal-normal model </b></b></b></b></b></b>


<b><b><b><b><b><b>The lognormal-normal model </b></b></b></b></b></b>


<b><b><b><b><b><b>The probit sampling model </b></b></b></b></b></b>


<b><b><b><b><b><b>Bayesian variable selection </b></b></b></b></b></b>


<b><b><b><b><b><b>Notation </b></b></b></b></b></b>


<b><b><b><b><b><b>Posterior model probability </b></b></b></b></b></b>


<b><b><b><b><b><b>The hierarchical uniform prior for models </b></b></b></b></b></b>


<b><b><b><b><b><b>Zellner's gpriors for model parameters </b></b></b></b></b></b>


<b><b><b><b><b><b>Intrinsic priors for model parameters </b></b></b></b></b></b>


<b><b><b><b><b><b>Bayes factors for normal linear models </b></b></b></b></b></b>


<b><b><b><b><b><b>Bayes factors for probit models </b></b></b></b></b></b>


<b><b><b><b><b><b>Bayesian predictive distribution of the net benefit </b></b></b></b></b></b>


<b><b><b><b><b><b>The normal-normal case </b></b></b></b></b></b>


<b><b><b><b><b><b>The case where c and e are independent </b></b></b></b></b></b>


<b><b><b><b><b><b>The lognormal-normal case </b></b></b></b></b></b>


<b><b><b><b><b><b>Optimal treatments for subgroups </b></b></b></b></b></b>


<b><b><b><b><b><b>Examples </b></b></b></b></b></b>


<b><b><b><b><b><b>Improving subgroup definition </b></b></b></b></b></b>


Dateiformat: EPUB
Kopierschutz: Adobe-DRM (Digital Rights Management)

Systemvoraussetzungen:

Computer (Windows; MacOS X; Linux): Installieren Sie bereits vor dem Download die kostenlose Software Adobe Digital Editions (siehe E-Book Hilfe).

Tablet/Smartphone (Android; iOS): Installieren Sie bereits vor dem Download die kostenlose App Adobe Digital Editions (siehe E-Book Hilfe).

E-Book-Reader: Bookeen, Kobo, Pocketbook, Sony, Tolino u.v.a.m. (nicht Kindle)

Das Dateiformat EPUB ist sehr gut für Romane und Sachbücher geeignet - also für "fließenden" Text ohne komplexes Layout. Bei E-Readern oder Smartphones passt sich der Zeilen- und Seitenumbruch automatisch den kleinen Displays an. Mit Adobe-DRM wird hier ein "harter" Kopierschutz verwendet. Wenn die notwendigen Voraussetzungen nicht vorliegen, können Sie das E-Book leider nicht öffnen. Daher müssen Sie bereits vor dem Download Ihre Lese-Hardware vorbereiten.

Bitte beachten Sie bei der Verwendung der Lese-Software Adobe Digital Editions: wir empfehlen Ihnen unbedingt nach Installation der Lese-Software diese mit Ihrer persönlichen Adobe-ID zu autorisieren!

Weitere Informationen finden Sie in unserer E-Book Hilfe.


Download (sofort verfügbar)

47,99 €
inkl. 19% MwSt.
Download / Einzel-Lizenz
E-Book bestellen