Question 4: What conclusion should we draw about tenderness?
The authors report that rates of tenderness were also lower with the longer needle throughout follow up, but not significantly (relative risk 0.60 (0.29 to 1.25), P=0.17).
We can conclude that the relative risk of tenderness in the population is between 0.29 and 1.25, so 1.0 is a possible value and the relative risk could be greater than 1.0 and still give rise to these data. The P value is quite big, greater than 0.05, so it is not significant, and greater than 1.0, so there is not even weak evidence for a difference.
What we cannot conclude is that there is no difference in tenderness. It may be that the sample is not larger enough to detect a difference which exists.
Back to Exercise: Reactions to immunisation using different sized needles.
To Applied Biostatistics index.
To Martin Bland's M.Sc. index.
This page maintained by Martin Bland.
Last updated: 22 November, 2006.