We want to commend Schumacher et al on their attempt to study the risks involved with carotid artery ligation. However, we have a major concern about the statistical methods used in this article. First, the authors compared two groups of infants (extracorporeal membrane oxygenation v nonextracorporeal membrane oxygenation) with regard to lateralizing abnormalities on the EEG using the one-tailed Fisher exact test and demonstrated statistically significant differences between the two in the incidence of attenuation, slowing, and diffuse abnormality with a unilateral emphasis (table 4). It is worth noting that the P value for the diffuse abnormality when using the one-tailed Fisher exact test actually calculates to be .06, demonstrating no significant difference.

This content is only available via PDF.
You do not currently have access to this content.