Invited session at 70th Biometric Colloquium IBS-DR, Lübeck, Germany

February 28 – March 01, 2024

organized by Matthias Schmid and Carsten Oliver Schmidt

Developing guidance for statistical analysis in observational research - a STRATOS Initiative update

1. TG2 Evaluating biostatistical methods before use - each phase is important  
Georg Heinze

2. TG3 Initial Data Analysis, Data Quality and Information Management to Improve Transparency of Statistical Analyses  
Carsten Oliver Schmidt

3. TG4 Recent developments in measurement error modelling  
Helmut Küchenhoff

4. STRATOS open science panel: The STRATOS open science panel  
Sabine Hoffmann, Anne-Laure Boulesteix

Abstract

The STRATOS initiative was launched in 2013 to provide accessible, evidence-based guidance for key topics in the design and analysis of observational studies. Guidance is provided to data analysts with varying levels of statistical background and experience. The focus is on health sciences research, but the content is also relevant for applications of statistics in other empirical sciences. STRATOS currently comprises nine topic groups (TGs) and twelve panels on a range of topics. This session will cover updates from TG2 Selection of variables and functional forms in multivariable analysis (Georg Heinze: Evaluating biostatistical methods before use - each phase is important), TG3 Initial data analysis (Carsten Oliver Schmidt: Initial Data Analysis, Data Quality and Information Management to Improve the Transparency of Statistical Analyses), TF4 Measurement error and misclassification (Helmut Küchenhoff: Recent developments in measurement error modelling), and from the STRATOS open science panel (Sabine Hoffmann, Anne-Laure Boulesteix).

Why would the session be of interest to the participants of the conference?

The session provides updates to guidance topics related to common issues of interest during statistical analysis, mainly related to observational studies.