Handling missing within-study correlations in the evaluation of surrogate endpoints.
Stat Med
; 42(26): 4738-4762, 2023 11 20.
Article
em En
| MEDLINE
| ID: mdl-37845797
ABSTRACT
Rigorous evaluation of surrogate endpoints is performed in a trial-level analysis in which the strength of the association between treatment effects on the clinical and surrogate endpoints is quantified across a collection of previously conducted trials. To reduce bias in measures of the performance of the surrogate, the statistical model must account for the sampling error in each trial's estimated treatment effects and their potential correlation. Unfortunately, these within-study correlations can be difficult to obtain, especially for meta-analysis of published trial results where individual patient data is not available. As such, these terms are frequently partially or completely missing in the analysis. We show that improper handling of these missing terms can meaningfully alter the perceived quality of the surrogate and we introduce novel strategies to handle the missingness.
Palavras-chave
Texto completo:
1
Base de dados:
MEDLINE
Assunto principal:
Modelos Estatísticos
Tipo de estudo:
Systematic_reviews
Limite:
Humans
Idioma:
En
Ano de publicação:
2023
Tipo de documento:
Article