Figure 1 shows the normal probability plot for the multiple regression model.
In the case of the leverage plots from the multiple regressions, the considerable variability in the health parameters relates to blood Hg concentrations primarily at the extreme ranges.
The modelling errors of the multiple regressions were also assessed by Q–Q plots, together with plots of the standardized residuals (the errors) with respect to the regression standardized predicted values.
Table 2 shows the results of the multiple regressions.
Table 3 displays the results of the multiple regression analysis.
Table 6 highlights the results of the multiple regression analysis.
Table 2 presents the results of the multiple regression analyses.
Thus, the residual plot indicates that there was no bias in the prediction of Vo2max of the CV-group using the multiple regression obtained in the V-group.
This was achieved by log-log regression, with the multiple regression tool of Stata 11.1 used to perform multiple linear regression of the logarithmic terms.
Further, the multiple regression explained 8.6% of the total variance.
