Footnote:
Nach Informationen von SSRN wurde die ursprüngliche Fassung des Dokuments September 15, 2022 erstellt
Description:
Deriving estimators from historical data is common practice in applied quantitative finance. The availability of ever larger data sets and easier access to statistical algorithms has also led to an increased usage of historical estimators. In this research note, we illustrate how to assess the quality of historical estimators based on their out-of-sample (ex ante) forecast performance. We analyse Swiss and US stock and bond data and find that optimal lookback window sizes exist, contrary to what would be expected from IID data. We close by outlining possible methodological refinements and possible factors driving the observed styled facts which might be discussed in more detail in updated versions of this research note