of these analyses. Bootstrapping is based on random sampling of the data and does not make assumptions about the shape of the sampling distribution. Bootstrapping also allows for the construction of more accurate confidence intervals than those derived from normal theory methods, and has been recently advocated (e.g., Edwards & Lambert, 2007; Hayes, 2013). We opted not to correct for multiple comparisons as the four outcomes are highly correlated and measure the same phenomenon (i.e., alcohol use), but in different ways.
