Apr 27, 2018

Suitable methods for evidence syntheses with very few studies

If only very few studies are available, the heterogeneity of study results cannot be reliably estimated. Recommendations for suitable methods for evidence synthesis now offer pragmatical problem-solving approaches, even in the event of sparse evidence.

If only 2 to 4 studies are available, the degree of heterogeneity of study results cannot be reliably estimated. This makes the choice of the model for meta-analyses in practical applications more difficult. However, suitable methods are available to nonetheless yield informative results: A group of authors including Ralf Bender and Guido Skipka from the German Institute for Quality and Efficiency in Health Care (IQWiG), as well as renowned experts in the field of meta-analyses, have now presented problem-solving approaches by means of examples from dossier assessments:

Bender R, Friede T, Koch A, Kuss O, Schlattmann P, Schwarzer G, Skipka G. Methods for evidence synthesis in the case of very few studies, Research Synthesis Methods 2018, DOI: 10.1002/jrsm.1297.

Further information:

Info Service (German)

Subscribe to daily updated information on projects, calls for tender, current vacancies and events as well as our press releases.

Register

Contact form

Questions about commissions, publications and press releases can be sent to us via this form.

Contact form