That’s the query posed through a paper through Wang, Sreedhara and Schneeweiss (2022). The authors mirror the findings from n=250 real-world knowledge research. The research had been replicated the use of 3 datasets: (i) Optum Clinformatics claims knowledge, (ii) IBM MarketScan Analysis Database claims knowledge, Medicare fee-for-service claims knowledge, and (iii) CPRD digital well being data. Key paper findings are underneath:
Authentic and replica impact sizes had been undoubtedly correlated (Pearson’s correlation = 0.85), a powerful courting with some room for development. The median and interquartile vary for the relative magnitude of impact (e.g., danger ratiooriginal/ danger ratioreproduction) is 1.0 [0.9, 1.1], vary [0.3, 2.1]. Whilst nearly all of effects are carefully reproduced, a subset aren’t. The latter will also be defined through incomplete reporting and up to date knowledge. Higher methodological transparency aligned with new steering would possibly additional make stronger reproducibility and validity evaluate, thus facilitating evidence-based decision-making
This paper gained the 2023 Award for Excellence in Well being Economics and Results Analysis Technique. You’ll be able to learn the total paper right here.