Network Meta-analysis with Stata - Course 2 - September


Lecturer: Aurelio Tobías, PhD


Biographical note: 

Aurelio Tobías

Senior Scientist at the Spanish Scientific Research Council in Barcelona and Visiting Research Fellow at the London School of Hygiene and Tropical Medicine. He has a long professional experience as medical statistician, as well as teaching epidemiological data analysis at postgraduate level. Dr. Tobías is a regular collaborator teaching meta-analysis courses at the Iberoamerican Cochrane Centre in Spain, Portugal and South America. 




Pedro Oliveira , Denisa Mendonça


Course description

Meta-analysis is commonly used to synthesize the effectiveness of an intervention from a collection of studies, but when there are not studies directly comparing two interventions, their comparative benefits cannot be estimated estimate. However, when information on the effectiveness of two interventions, named B and C, is available in comparison to a common comparator A, an indirect treatment comparison may be used to estimate the effectiveness of B compared with C.

Approaches to meta-analysis have been developed to estimate the effect of multiple interventions, taking into account the full network of available studies and simultaneously incorporating direct and indirect comparisons.

The aim of this course is to introduce, in a friendly and easy way, the main statistical techniques to analyse a network meta-analysis using the network suite of Stata commands.


Course outline


Day 1

9:00 to 9:30     Introduction: why do we need indirect comparisons?

9:30 to 10:30   Type of comparisons in meta-analysis: the Bucher’s method.

10:30 to 11:00  Coffee break

11:00 to 12:30  Meta-regression models for indirect and mixed treatment effects

12:30 to 13:30  Lunch break.

13:30 to 15:00  Full network meta-analysis: models of consistency and inconsistency

15:00 to 15:15  Coffee break.

15:15 to 16:00  Presenting results from a network met-analysis: the PRISMA-NMA guideline.

16:00 to 18:00  Network meta-analysis with Stata using the network commands.


Day 2

9:00 to 10:30    Practical exercises using Stata.

10:30 to 11:00  Coffee break

11:00 to 12:30  Practical exercises using Stata (continuation).

12:30 to 13:00  Course summary.



The course is intended for researchers, physicians, clinicians, public health professionals, epidemiologists and biostatisticians, from public and private institutions who need to apply network meta-analysis. Previous experience with traditional meta-analysis and familiarity with Stata would be desired.



Caldwell DM, Ades AE, Higgins JPT. Simultaneous comparison of multiple treatments: combining direct and indirect evidence. Br Med J. 2005; 331: 897-900.


Higgins JPT, Jackson D, Barrett JK, Lu G, Ades AE, White IR. Consistency and inconsistency in network meta-analysis: concepts and models for multi-arm studies. Res Syn Meth. 2012: 3; 98-110.


Sterne JAC. Meta-analysis in Stata: An Updated Collection from the Stata Journal. 2nd Edition. Stata Press: College Station, TX, 2016.







Language: English


Tuition Fee

Course 2: Network Meta-analysis with Stata

Fee: 150€; Reduced Fee: 135€

Combined Registration (Course 1 + Course 2):

Fee: 225€; Reduced Fee: 200€


Reduced Fees:

- Members of ‘Sociedade Portuguesa de Estatística’ e ‘Associação Portuguesa de Epidemiologia’

- Students from Public Health MSc and PhD

- Students from Global Public Health PhD

- Students from Applied Maths and Mat PDMA PhD

- Students from Public Health Internships


Day 1 (28th sep): 9h00-18h00; Day 2 (29th sep): 9h00-13h00;
non applicable
Start date:
End date: