Question 1: What do the authors mean by '95% confidence interval -0.19 to 1.23'?
They are using the data as a sample of a larger population of children in general. They want to use the sample to estimate the difference in mean IQ between breastfed and non-breastfed children in that wider population. They estimate that in the whole population, the difference in mean IQ, breastfed minus non-breastfed, is 0.52 points on the IQ scale. However, some samples will give estimates which are too high, others will give estimates which are too low. For this reason, they produce an interval estimate, a range of possible values for the difference in the popluation. They estimate that breastfed children have mean IQ between 0.19 points lower and 1.23 points higher than the mean for non-breastfed children.
The confidence interval is chosen so that, from all the possible samples of children, 95% of the confidence intervals calculated would include the difference in the whole population.
Back to Exercise: Effect of breast feeding on intelligence.
To Applied Biostatistics index.
To Martin Bland's M.Sc. index.
This page maintained by Martin Bland.
Last updated: 6 November, 2006.