Exercise: Endarterectomy versus stenting using CMA2, answer 2

Question 2: On the CMA2 data entry screen, what is missing for the study of Brooks et al. (2004)? Why is it missing?

Suggested answer:

You should see something like this:

Study name Endarterectomy
Events
Endarterectomy
Total N
Stenting
Events
Stenting
Total N
Odds ratio Log odds
ratio
Std Err I J
Naylor 1998 0 12 5 11 0.047 –3.052 1.554                    
Wallstent 2001 5 112 13 107 0.338 –1.085 0.545        
CAVATAS 2001 25 253 25 251 0.991 –0.009 0.298        
Brooks 2001 1 51 0 53 3.178 1.156 1.645        
Brooks 2004 0 42 0 43                    
SAPPHIRE 2004 8 167 7 167 1.150 0.140 0.530        
EVA-3S 2006 10 262 25 265 0.381 –0.965 0.385        
SPACE 2006 38 584 46 599 0.837 –0.178 0.227        
BACASS 2007 1 10 0 10 3.316 1.199 1.693        
ICSS 2009 43 857 72 853 0.573 –0.557 0.199        

What I noticed was that for Brooks et al. (2004) there is no odds ratio, log odds ratio, or standard error. There is no odds ratio because there are no events in either group. Hence there is no information about the treatment difference and we cannot estimate an odds ratio.

If you put just one event in either of the groups, CMA2 will produce something, as it has for Brooks 2001 and BACASS, each of which have only one event, for endarterectomy, and for Naylor 1998, which has events only for stenting. The standard errors for these log odds ratios are large, because they are poorly estimated.


Back to question.

Back to Systematic Reviews index.

To Martin Bland's home page.

This page maintained by Martin Bland.
Last updated: 19 February, 2010.

Back to top.