Ex post risk report

From Flametree Technologies
Revision as of 05:15, 12 February 2020 by Fiasys (talk | contribs)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to navigation Jump to search

The following table describes the ex-post risk statistics currently calculated by the FIA engine.

Statistic Notes Formula
mean Average return over N samples <math>\mu=\frac{1}{N}\sum_i{r_i}</math>
sigma Standard deviation of return over interval. Also referred to as volatility, sigma. <math>\sigma=\sqrt{\frac{1}{N}\sum_i{(r_i-\mu)}^2}</math>
population_sigma Sample standard deviation of return. Includes Bessel's sample count correction N-1 instead of N. <math>sd=\sqrt{\frac{1}{N-1}\sum_i{(r_i-\bar{x})}^2}</math>
variance Square of standard deviation of return over interval. <math>\sigma^2</math>
population_variance Square of sample standard deviation of return over interval. <math>{sd}^2</math>
tracking_error Standard deviation of active return (portfolio return minus benchmark return)
information_ratio Active return (portfolio return minus benchmark return) divided by tracking error
covariance Covariance of portfolio return against benchmark return
correlation Correlation of portfolio return against benchmark return
correlation_squared Square of correlation of portfolio return against benchmark return
beta Beta of portfolio against benchmark
omega Omega statistic
jensen_alpha Jensen's alpha
Sharpe ratio Sharpe ratio for portfolio return
Active Sharpe ratio Sharpe ratio for portfolio return against benchmark return <math>S = \frac{R_P-R_B}{sd}</math>
Treynor ratio <math>T = \frac{R_P-R_B}{\beta}</math>
upside_volatility
downside_volatility
Skewness A measure of the asymmetry of the distribution of returns about their mean <math>S=\frac{N}{(N-1)(N-2)}\sum_{i=1}^N\left[\frac{(r_i-\bar{r})}{sd}\right]^3</math>
Kurtosis A measure of the "peakedness" of the distribution of returns <math>S=\frac{N(N+1)}{(N-1)(N-2)(N-3)}\sum_{i=1}^N\left[\frac{(r_i-\bar{r})}{sd}\right]^4</math>

<math>+\frac{3(N-1)(N-1)}{(N-2)(N-3)}</math>