Correlation, co-dependency and risk aggregation [34]

Go to: Summary | Previous | Next   
Bullet points include: Normal (Pearson) correlation coefficient: Spearman’s rank correlation coefficient: Here qt and rt are ranks of xt and yt. Kendall’s tau: Concordant: (xi > xj and yi > yj) or (xi < xj and yi < yj). Last two involve only ordering of observations, i.e. (for bivariate distributions) their copula and not their marginal. Parameterisation of some copula families has one-to-one correspondence with one or other of these alternative ways of measuring co-dependency

Contents | Prev | Next | ERM Lecture Series

Desktop view | Switch to Mobile