Fig. 1

Example of a principal component analysis performed in a single window from the first dataset [39]. The left figure shows the mean positive and negative mental states of the assessment occasions in this window (indicated by black dots), as well as the first principal component (dotted line). The blue arrow reflects the vector that was inferred from the principal component analysis: the length of the arrow corresponds to the proportion of variance explained by the first principal component, while the direction of the arrow corresponds to the skewness of the scores projected on this component. The skewness, illustrated in the right plot, is directed towards the left. Together, the length and direction of the vector can be used to infer the predicted change in mental states. Here, we would predict an increase in negative mental states (0.7) and a larger decrease in positive mental states (-0.9). A similar, more detailed explanation of this method was described by Lever and colleagues [33]