Network meta-analysis

[Joaquin Baruch]

Hello all,

I'm trying to run network meta-analysis in Stata and I'm running into a problem that might be related to my data format. I was wondering if you could help me with the following:

I have my data in long format and some of my trials have more than one control group or more than one treatment group for a given vaccine. Example, code, and error message follows:

When I run the network setup command:
network setup number_sick number_animals, studyvar(Study) trtvar(vaccine_) or

I get the following error message:
variables Study vaccine_ do not uniquely identify the observations

Please let me know if you have any recommendations.?
Thank you,
Joaquin

Study	number_animals	number_sick	vaccine_
1	48	20	Control
1	126	1	Control
1	305	23	Control
1	2809	309	Control
1	887	186	Control
1	48	16	A
1	126	1	A
1	305	11	A
1	2809	309	A
1	887	151	A
2	107	1	Control
2	107	1	B
2	107	4	B
2	107	1	B
3	103	42	Control
3	51	16	Control
3	50	15	Control
3	49	11	A
3	48	16	A