Skip to main content

Table 4 Comparison of the intercept and slope to explain the effect of β2-agonists by study means

From: Many continuous variables should be analyzed using the relative scale: a case study of β2-agonists for preventing exercise-induced bronchoconstriction

 

Intercept

Slope

χ2(3 df) *

P *

AIC **

Uniform effect (absolute scale)

21.4

  

323.5

Intercept and slope

16.4

−0.24

8.52

0.036

 

Slope (relative scale)

−0.77

11.9

0.010

333.0

  1. The intercept and the slope were calculated with a linear mixed-effects model using the type of β2-agonist as the grouping variable. The studies were weighted by the square root of the number of participants. For the identity of the 44 trials and their references, see Additional file 1: Table S2 and [11]. Abbreviations: pp., percentage points
  2. * Anova test comparing the model to the model in the row above
  3. ** AIC, Akaike information criterion. AIC estimates the relative quality of statistical models, lower AIC value is preferable