Skip to main content

Table 2 Linear regressions that predict the three chronic diseases from item weight and nutrient diversity (plus control variables such as income, gender, age, education level)

From: Large-scale and high-resolution analysis of food purchases and health outcomes

FeatureCoefficientStd. errorp-value
Hypertension
α (intercept)0.55820.064<0.001
Calorie consumption0.302280.070<0.001
Nutrient diversity−0.51820.069<0.001
Income0.06150.0410.131
%Females−0.22100.038<0.001
Average age0.16270.037<0.001
Education−0.23090.041<0.001
Durbin–Watson stat. = 2.033Adj \(R^{2} = 0.377\)
Cholesterol
α (intercept)0.54650.059<0.001
Calorie consumption0.13950.0640.03
Nutrient diversity−0.49430.064<0.001
Income0.00170.0370.96
%Females−0.23640.035<0.001
Average age0.117900.0340.001
Education−0.17850.037<0.001
Durbin–Watson stat. = 1.981Adj \(R^{2} = 0.344\)
Diabetes
α (intercept)0.75820.038<0.001
Calorie concentration0.13010.028<0.001
Nutrient diversity−0.63530.043<0.001
Income−0.07900.0340.019
%Females−0.36930.031<0.001
Average age−0.06060.0300.042
Education0.10470.0320.001
Durbin–Watson stat. = 1.964Adj \(R^{2} = 0.585\)