Statistical analysis including multiple regression, 2-sample Student's t-tests and chi-square tests was performed using DataDesk 6.1.1 (Data Description Inc, Ithaca, NY); p ≤ 0.05 was considered statistically significant.
To test if either of the two SDS subsets of items was a stronger predictor of SDS total score for the total sample, multiple regression was applied to the sample's scores on Melancholia and Nonmelancholia SDS items, and these were regressed against the total SDS score.
In figure 1, we present the bias (panels A D), the variance (panels E H) and the RMSE (panels I L), respectively, using naïve multiple regression under different sample sizes.
Pearson's correlation coefficient, multiple regression analysis, independent samples t-test and one-way ANOVA were used to analyze the data collected.
With analysis by partial least squares multiple regression over 11 sampling dates and 39 fields where both ground and PALS data were well represented, only SOC contributed significantly to the regression of SWC beyond the variance all soil variables had in common.
However, a post hoc sample size calculation for multiple regression analysis revealed that our sample size gave us 80% power to detect a R2 of 0.049 (for both HRQOL and lifestyle advice), assuming a type one error rate of 5% and a maximum of 4 factors in the model.
Multiple regression analyses included a sample with missing values for the adjusted variables.
Multiple regression models included a sample with unknown values for these adjusted variables.
In order to delineate the influence of disease on functioning in the GRAS sample, multiple regression analyses have been employed.
Finally, we applied multiple regression analysis to identify sample characteristics that may explain the differences between Baseline and Historical moderate- and vigorous-intensity scores.
