[Skip to Content]
Access to paid content on this site is currently suspended due to excessive activity being detected from your IP address 54.197.142.219. Please contact the publisher to request reinstatement.
[Skip to Content Landing]
Citations 0
Letters
February 25, 1998

Effects of Age and Ethnicity on the Link Between APOE ∊4 and Alzheimer Disease—Reply

Author Affiliations
 

Margaret A.WinkerMD, Senior EditorIndividualAuthorPhil B.FontanarosaMD, Senior EditorIndividualAuthor

JAMA. 1998;279(8):580-582. doi:10-1001/pubs.JAMA-ISSN-0098-7484-279-8-jbk0225

In Reply.—As pointed out by Dr Ewbank, comparisons of Table 3 and Figure 4 are inappropriate because the results reported in Table 3, although adjusted for age and study, do not consider the possibility of interaction among age, sex, and APOE genotype. However, there is significant interaction among Caucasians exemplified by the results in Figures 1 through 3. On the other hand, the logistic regression results in Figure 4 were not adjusted for study because of sparse data in several of the individual studies. Strictly speaking, the results in Figure 4 more accurately portray the data than those in Table 3, but Table 3 was included because the data therein (1) illustrate our hierarchical approach to tackling the issue of interaction, (2) are more stable and easily interpretable than age- and sex-specific APOE genotype relative risks, and (3) are readily comparable to estimates in other studies. It is also important to recognize that even in this large data set, some of the interaction tests succumbed to power problems resulting in unstable risk estimates.

First Page Preview View Large
First page PDF preview
First page PDF preview
×