Creating portfolio risk and return models [19]

Go to: Summary | Previous | Next   
Bullet points include: Problem: importance from a risk perspective also related to magnitude Remember kurtosis is scale independent PCA offers magnitude (focusing on variance), ICA offers meaningfulness (focusing on, e.g., kurtosis) Ideally we want to blend the two, e.g. by: Recasting PCA along the lines of projection pursuit (with an importance criterion involving maximising contribution to variance), and then Choosing a different importance criterion that blends together variance and (e.g.) kurtosis

Contents | Prev | Next | ERM Lecture Series

Desktop view | Switch to Mobile