Hypothetical versus empirical suicide fluctuations: The Spanish case.

<p><i>Note</i>. We compare three datasets: The actual empirical dataset <i>a1</i> (suicide rates per 100,000 population), a simulated dataset without changes in intensity of cohort effects (i.e. hysteresis/stability over the life course) <i>a2</i>, and the difference between cells <i>a3</i>. Now consider <i>b1</i> and <i>b2</i>, the residuals of the logged values of datasets <i>a1</i> and <i>a2</i> in the model (AP) (we suppress the linear combination of age and period dummies). <i>b1</i> shows some cohort effects, that are ‘imperfect’ compared to <i>b2</i> the expected values under the hypothesis of a pure APC without h effect. In these tables, the red cells are the high values of suicide and the blue cells the relatively protected groups. <i>b3</i> presents the differences between empirical <i>b1</i> and theoretical <i>b2</i>, and following the diagonally changing colours, we can detect temporal stability/changes of cohort fluctuations.