Question 1: What do the authors mean by adjustment for maternal intelligence?
It may be that the outcome of interest, the baby's IQ, is related to the mother's IQ. Indeed, we would expect this to be the case, due to both heredity and environemnt. The authors want to estimate the effect of breastfeeding on the baby's IQ for women who have the same IQ themselves. We sometimes refer to this as holding mother's IQ constant.
If mother's and baby's IQ are related, the adjustment should make the estimate of the effect of breastfeeding better, having a narrower confidence interval.
If mother's IQ and breastfeeding are related, perhaps because women with higher IQ are more likely to choose to breastfeed, the adjustment may change the estimate of the effect of breastfeeding, as well as producing a narrower confidence interval.
Back to Exercise: Breast feeding, maternal intelligence, and babies' intelligence.
To Applied Biostatistics index.
To Martin Bland's M.Sc. index.
To Martin Bland's home page.
This page maintained by Martin Bland.
Last updated: 6 November, 2006.
Back to top.