Question 4: Assuming the data are correct, why are “r = -0.45” and “r = -0.22” obvious misprints on this graph?
The correlation coefficients for vocabulary should be positive, because older people have a larger vocabulary. The regression line slopes upwards.
Following a letter from Martin Bland, the following correction was printed in the Lancet, 18 March 2000: ‘. . . the correlation coefficients for vocabulary scores in the figure should be r = 0.45 for patients with mesial temporal-lobe epilepsy (MTLE) and r = 0.22 for controls . . .'.
Back to Exercise: Vocabulary, age, and epilepsy.
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: 1 December, 2006.
Back to top.