Abstract
One of the common obstacles in the analysis of nutrient data is the high correlation between nutrients (N) and total caloric intake (T) when used in a traditional multivariate model. This results in difficulties in separating the effect of N from the effect of T when they are simultaneously used in a statistical model. Using computer simulations and data from a case control study, we show that nutrient density N/T is weakly correlated with T even when N and T are highly correlated. As nutrient density has intuitive appeal to nutritional scientists and it is increasingly important to separate out the effect of specific nutrients from the effect of total calories on various health outcomes, the multivariate nutrient density model which includes both N/T and T should be utilized more often in nutritional epidemiology.
Original language | English (US) |
---|---|
Pages (from-to) | 765-774 |
Number of pages | 10 |
Journal | Nutrition Research |
Volume | 14 |
Issue number | 5 |
DOIs | |
State | Published - May 1994 |
Externally published | Yes |
Keywords
- Collinearity
- Nutrient
- Nutrient density
- Total Calories
ASJC Scopus subject areas
- Endocrinology, Diabetes and Metabolism
- Endocrinology
- Nutrition and Dietetics