Table 2. Statistical models test the hypothesis.
| Model 1. Effect of psychological variables | Model 2. Effect of food preferences | Model 3. Interaction between body fat and sex | |
|---|---|---|---|
| Sex (Male) | 0.87 (-0.07, 1.81)† | 1.0 (0.05, 1.9) ‡ | -0.66 (-2.79, 1.46) † |
| Fat percentage (%) | 0.02 (0.002, 0.037)‡ | 0.02 (0.004, 0.038) ‡ | -0.23 (-0.41, -0.04) ‡ |
| Sex*Fat% (Male) | -0.03 (-0.06, 0.005) † | -0.03 (-0.06, -0.001) ‡ | 0.16 (-0.15, 0.48) |
| Sex*Fat%^2 (Female) | 0.01 (0.002, 0.017)*** | ||
| Sex*Fat%^2 (Male) | 0.004 (-0.01, 0.02) | ||
| Sex*Fat%^3 (Female) | -0.001 (-0.0001, -0.00002) ‡ | ||
| Sex*Fat%^3 (Male) | -0.0001 (-0.0003, 0.0001) | ||
| Distress | -0.05 (-0.20, 0.10) | ||
| Uncertainty | 0.11 (-0.07, 0.28) | ||
| Lack of sleep | -0.06 (-0.18, 0.07) | ||
| Sadness | 0.01 (-0.13, 0.16) | ||
| Anxiety | 0.01 (-0.14, 0.16) | ||
| Twelve factors of food | -0.12 (-0.27, 0.03) to 0.10 (-0.04, 0.25) | ||
| Adj R^2 | 0.001 | 0.04 | 0.08 |
| Root MSE | 0.76 | 0.75 | 0.74 |
The regression coefficients (95%CI) are presented in a summary of the regression models analyzed. To ensure the integrity of our analysis, we addressed potential collinearity issues (detailed in the text) and limited our examination to relationships among variables based on established clinical criteria. The table includes two key statistical measures for each model: the Adjusted R^2, representing the proportion of variance explained by the model (adjusted for the number of predictors), Mean Square Error to quantify the standard deviation of the residuals, and measuring the model’s accuracy. Adj R^2: Adjusted coefficient of determination. Root MSE: Root of Mean Square Error.
†p<0.10
‡p<0.05
***p<0.01.