813 reputation
19
bio website
location Germany
age
visits member for 1 year, 9 months
seen 8 hours ago

Monte Carlo, risk, QMC, statistical efficiency, high dimensional approximation...


May
31
revised George Soros models
added 1685 characters in body
May
31
comment VaR for portfolio of funds
@quant_dev: For example, yes, that's the first & most basic step, but that will only capture some of the discrepancies since it's a static view. Then you can feed it back in your forecasts as an independent component. Improving on this one could first model dependencies with the other variates, and then sample joint forecasts. But to also capture temporal discrepancies, such as rebalancings, you should compare/model the running forecasts (returns conditional on the statistics on previous data) historically, in a kind of backtesting, not just the 2 valuations series. I'll expand if too cryptic.
May
31
comment George Soros models
@Quant Guy: whops it seems that I downvoted by error, I want to upvote instead (although I disagree on some points), could you please edit to unlock vote changes? Thanks!
May
31
answered George Soros models
May
30
answered VaR for portfolio of funds
May
30
answered Is Unexpected Loss ever used in Basel II?
Apr
25
revised Transformation to reduce standard deviation without changing median
deleted 4 characters in body
Apr
24
revised Transformation to reduce standard deviation without changing median
added 144 characters in body
Apr
24
answered Transformation to reduce standard deviation without changing median
Apr
17
revised Stress testing covariance
added 81 characters in body
Apr
17
revised Stress testing covariance
added 26 characters in body; edited tags
Apr
16
asked Stress testing covariance
Apr
9
comment Iterating through every path of a Trinomial Tree
So you want to condition on a specific path end?
Apr
9
answered Iterating through every path of a Trinomial Tree
Mar
19
revised Reasoning behind multiple names for the equivalent risk measures AVaR/ETL/ES/CVaR
added 83 characters in body
Mar
19
revised Reasoning behind multiple names for the equivalent risk measures AVaR/ETL/ES/CVaR
added 136 characters in body
Mar
19
revised Reasoning behind multiple names for the equivalent risk measures AVaR/ETL/ES/CVaR
added 22 characters in body
Mar
19
revised Reasoning behind multiple names for the equivalent risk measures AVaR/ETL/ES/CVaR
added 44 characters in body
Mar
19
answered Reasoning behind multiple names for the equivalent risk measures AVaR/ETL/ES/CVaR
Mar
14
comment Calculate the expectation of a shift CDF
@nkhuyu are you sure they were asking for $F_X(X+a)$ instead of $F_{X+a}(X+a)$? That would require extra care in specification, instead of just saying $F(X+a)$ which should refer to the latter... One could infer from the level of other questions :-)