APMA 3120 Chapter Notes - Chapter 6: Dependent And Independent Variables, Confounding, Relative Risk
Document Summary
Likewise for girls, the rate of hyperactivity is . 25, regardless of sugar intake. However, strong evidence of a relationship appears to exist when the two groups are combined: the hyperactive rates are . 43 for low sugar intake vs. 59 for high sugar intake. This phenomenon is known as simpson"s paradox, which describes the apparent change in a relationship in a two-way table when groups are combined. In our hypothetical example, boys tended to consume more sugar than girls, and also tended to be more hyperactive than girls. This results in the apparent relationship in the combined table. When the response variable is for the occurrence of something like illness or death, each rate may be referred to as a risk, and the ratio of rates is the relative risk. Odds give a ratio of occurrence vs. non-occurrence using whole numbers. i.