Skip to main content

Table 1 Simulation results for model diagnostics when α1 = 0

From: Using marginal standardisation to estimate relative risk without dichotomising continuous outcomes

  ε~Normal(0, 1)ε~Logistic(0, 1)
ModelPercentilesProportion of rejection at 5% significance levelProportion of rejection at 5% significance level
Normal Linear Model aNA c0.0530.822
Probit Model b0.0750.0370.043
0.150.0390.032
0.30.0410.042
0.50.0330.038
0.70.0280.039
0.850.040.044
0.9250.0380.029
Logistic Linear Model aNA c0.0520
Logit Model b0.0750.0390.032
0.150.0360.039
0.30.0360.038
0.50.0380.034
0.70.0340.034
0.850.0420.052
0.9250.0280.041
  1. aLilliefors corrected Kolmogorov-Smirnov test were used to test whether residuals from normal linear model had a normal distribution, and Kolmogorov-Smirnov test was used to test whether residuals from logistic linear models had a logistic distribution. bPregibon link test was used to test whether probit or logit link was appropriate. cThe same normal (or logistic) linear model is applied across different threshold values.
\