Footnote:
Nach Informationen von SSRN wurde die ursprüngliche Fassung des Dokuments November 18, 2022 erstellt
Description:
The common method of calculating economic magnitudes is to multiply the regression coefficient by the population standard deviation for the variable of interest. We show that this method is problematic in many finance settings, where researchers typically use granular group effects. For common finance variables, the population standard deviation is often much larger than the within-group variation that identifies the regression coefficient, and within-group changes of this magnitude are rare. Thus, without additional assumptions, the common approach significantly inflates the economic magnitude of the identified effect. We provide several approaches to measure within-group variation for economic magnitude calculations