Biostatistics Short Course: Dose-Response Meta-Analysis: Models and Applications

This half-day in-person course offers an in-depth understanding of concepts and methodologies for conducting dose-response meta-analyses using either individual patient data or aggregated (summarized) data. The course covers a broad range of topics, including statistical models tailored for dose-response meta-analyses of various endpoints such as continuous, binary, and time-to-event data. Participants will explore various dose-response strategies, including linear trends, polynomials, splines, hypothesis testing, point-wise confidence intervals, and techniques for assessing heterogeneity. The course combines lectures with hands-on computer sessions, focusing on the selection of analysis methods, interpretation of results, and presentation of dose-response findings in both tabular and graphical formats. Analyses will be conducted using R or Stata software.

Audience:

This course is aimed at researchers and postgraduate students in biostatistics, epidemiology, and related fields. Knowledge of basic statistical concepts (i.e. central limit theorem, test of hypothesis, confidence intervals), and mixed effects linear regression models is assumed. Participants should have some prior experience of using either R or Stata, though not necessarily in the context of meta-analysis.

Speaker:

Nicola Orsini, PhD, Karolinska Institutet