Skip to main content

Table 4 Results of multivariate adaptive regression splines (MARS) analysis showing model, dependent variable, type

From: Effects of weather conditions, light conditions, and road lighting on vehicle speed

Model Results
Weather conditions and dependent variable GCV RSS RSq
 Average speed 16.8 2,734,006 0.97
 Speed difference 16.8 2,734,006 0.71
 Average speed 20.2 549,327 0.97
 Speed difference 20.2 549,327 0.66
 Average speed 31.1 632,439 0.92
 Speed difference 31.1 632,439 0.59
  1. GCV generalized cross validation, RSS residual sum-of-squares (RSS) of the model, and Rsq R-squared of the model. For more information see Milborrow (2015). Model: dependent variable ~ natural light condition (day, darkness, twilight) + distance to the nearest intersection + road width + posted speed limit + road surface temperature + year + month + presence of road lighting or not + amount of precipitation + weather condition (clear, rain, snow) when applicable. Model with the best fit shown in italics