T16 — Compar­ing meth­ods using real and simu­lat­ed data: chal­lenges and best practices

Day, Time, Duration

Thurs­day after­noon, 2 pm‑6 pm, 4h

Language offered

English

Short Descrip­tion

The course provides an overview of the method­ol­o­gy of compar­a­tive stud­ies with a focus on statis­ti­cal meth­ods, but at the inter­face with other GMDS-relevant fields such as machine learn­ing and bioin­for­mat­ics. The target audi­ence consists of readers/users of compar­a­tive stud­ies as well as method­olog­i­cal junior scien­tists* who wish to design and conduct compar­a­tive stud­ies them­selves. In partic­u­lar, the follow­ing topics will be covered: 1. Design of a compar­a­tive study (of meth­ods), influ­ence on results and danger of cherry-picking and non-replicable method­olog­i­cal research results 2. “Neutral compar­a­tive stud­ies” as an ideal, diffi­cul­ties and partial solu­tions 3. Report­ing of compar­a­tive stud­ies 4. Simu­la­tion stud­ies in method­olog­i­cal research: design, prac­ti­cal rele­vance, neutral­i­ty, report­ing 5. Data-driven simu­la­tion stud­ies in appli­ca­tions as deci­sion support for choice of meth­ods Planned are course units in “lecture style” as well as short hands-on sessions in R on the above topics. Liter­a­ture: M. Herrmann, P. Prob­st, R. Hornung, V. Juri­novic, A.-L. Boulesteix, 2021. large-scale bench­mark study of survival predic­tion methods.

Orga­niz­er

Moritz Herrmann

Insti­tu­tion

Insti­tute for Medical Infor­ma­tion Process­ing, Biom­e­try, and Epidemi­ol­o­gy, LMU Munich, München

Contakt

moritzherr.uni [at] googlemail.com

boulesteix [at] ibe.med.uni-muenchen

c.niessl [at] ibe.med.uni-muenchen.de

Addi­tion­al Speaker

Christi­na Nießl

Insti­tu­tion

Insti­tute for Medical Infor­ma­tion Process­ing, Biom­e­try, and Epidemi­ol­o­gy, LMU Munich, München