Relative growth rates decreased significantly with relative degree of dominance by P. gracilis (linear regression, Ln(relative growth rate) = 0.75−0.98 / Ddiff, F36,1 = 9.3, p = 0.004, R = 0.21).
The association between C-AD and microalbuminuria was estimated by multiple linear regression, and relative risks (RRs) for cardiovascular mortality were estimated by Cox proportional hazards analyses.
For maximum likelihood estimation in a mixed effects linear regression, asymptotic relative efficiencies (RE) of unequal versus equal cluster sizes in terms of the D-criterion and Ds-criteria are derived.
Primer efficiencies were estimated via linear regression and relative expression ratios (R) were calculated according to Pfaffl [ 62].
Plotted values represent the average results of the two trials performed by each subject; a linear regression curve relative to the entire group's data (right-hand side) and to the three subgroups' data (left-hand side) is also represented.
Graphing, linear regressions and relative risks were prepared with GraphPad (version 5.d; Graphpad Software Inc., CA, USA).
We then estimated linear and quadratic coefficients of selection using linear regressions of relative fitness on standardized development indices and visualized the pattern of selection using the derived models (Lande and Arnold 1983; Stinchcombe et al. 2008).
For these analyses, directional selection gradients (β i) were estimated as the standardized partial linear regression coefficients of relative fitness as a function of relative resistance and plant diameter.
Note: at substrate concentrations below the K m, the slope of the linear regression reflects the relative velocity of the reaction (proportional to the K cat / K m of the particular enzyme-substrate pair).
