![](https://csdnimg.cn/release/download_crawler_static/86946807/bg1.jpg)
eAppendix
If one or both of the exposures or the effect modifier has more than two levels, additional rows and/or
columns could be added to Tables 1 or 3. In that case more than one measure of interaction on an
additive or multiplicative scale can be calculated and presented. eTable 1 presents an example of
interaction between one dichotomous exposure and one exposure with three categories. In this study
the interaction between parity (>= 1 children, 0 children) and breast density (<5%, 5-25%, >25%) on
breast cancer risk was investigated in a nested case-control study
27
.