Extrapolating baseline trend in single-case data: Problems and tentative solutions

Abstract

Single-case data often contain trends. Accordingly, in order to account for baseline trend, several data analytical techniques extrapolate it into the subsequent intervention phase. Such an extrapolation led to forecasts that are smaller than the minimal possible value in 40% of the studies published in 2015 that we reviewed. In order to avoid impossible predicted values we propose extrapolating a damping trend, when necessary. Furthermore, we propose a criterion for determining whether extrapolation is warranted and, if so, how far away it is justified to extrapolate baseline trend. This criterion is based on the baseline phase length and the goodness of fit of the trend line to data. The proposals are implemented in a modified version of an analytical technique called Mean Phase Difference. We use both real and generated data to illustrate how unjustified extrapolations may lead to inappropriate quantifications of effect, whereas the proposals help avoiding these issues. The new techniques are implemented in a user-friendly website via Shiny applications offering both graphical and numerical information. Finally, we point to an alternative not requiring trend line fitting or extrapolation.