Reputation
464
Top tag
Next privilege 500 Rep.
Cast close & reopen votes
Badges
2 10
Impact
~3k people reached

  • 0 posts edited
  • 0 helpful flags
  • 60 votes cast
Mar
6
answered What does tradable asset mean?
Mar
3
comment What to use as portfolio diversification measure?
I agree with SRKX but would even go one step further. It does not make a lot of sense (at least to me) to discuss diversification unless you specify a risk measure. Then the perfectly diversified portfolio is one which minimises your particular risk measure.
Feb
7
comment Get distribution for aggregate loss using Monte Carlo
I am still not sure I understand because what you seem to want sounds somewhat unusual. Normally people fit frequency and severity and then simulate exactly to avoid doing a fit to the aggregate distribution. Why do you need a parametric representation of the aggregate losses, if you can simulate them?
Feb
6
comment Get distribution for aggregate loss using Monte Carlo
And by the way, given that losses from operational risk often are very heavy tailed, I would consider carefully whether a distribution for such losses should have finite variance
Feb
6
comment Get distribution for aggregate loss using Monte Carlo
Your question is not clear to me, what do you want to know: 1. Do you want to know how to do a Monte-Carlo simulation given a frequency and severity distribution? 2. Do you want to know how to calibrate a specific parametric distribution to your data at hand? Or do you want to know how to choose such a parametric distribution in the first place?
Jan
29
comment Which sports are generally the best for trading on betting exchanges for a profit?
Interesting read and good advice for beginners. Some of it should generalise to betting on other underlyings as well.
Jan
19
answered Longevity risk modelling
Oct
15
awarded  Yearling
Oct
15
answered Problem when calculating the daily return on a forex trade, what is the best way to do such a calculation?
Sep
19
answered Why would there be a positive risk-free rate?
Aug
27
awarded  Critic
Jul
10
comment How to see the impact of one variable on a set of other variables?
Richard is right this sounds like a job for regression analysis. If you would like to bet money on the outcome be aware that you attempt a very difficult thing and there are many pitfalls. The main problem is the large number of potential factors and their complex and time dependent interaction. I guess you can start with any book covering regression and time series analysis. In addition there are a gazillion of academic and other papers. A quick search with the keywords "shocks" "equities" and "regression analysis" gave me about 6m hits
Jul
10
comment What are the implication of a negative risk-free rate on SML?
Second comment: Does CAPM still make any sense as a model if risk free rates are negative? One could hold cash in physical notes in a safe vault earning zero which means negative risk free rates create arbitrage opportunities. So the fact that negative risk free rates are possible at all can only be explained with features not contained in the CAPM model, such as the cost of safe bank vaults or the fact that there is no risk-free asset in the first place.
Jul
10
comment What are the implication of a negative risk-free rate on SML?
First Comment: Are negative rates really consistent with the assumptions underlying CAPM? For example why would anyone invest risk-free instead of consuming wealth immediately?
Jul
10
answered How to see the impact of one variable on a set of other variables?
May
28
comment List of financial derivatives Ito's Lemma does not apply
Probilitator: Can you give a reference for the smoothness result for $g(t,x)$? I was just looking for something in that direction.
May
28
comment Is there any other way to measure option pricing model performance than proximity to market prices?
I would like to support Matt's comment by pointing out the "no-arbitrage" principle. Due to this principle an option price is closely connected with the underlying's price. Whenever no-arbitrage applies option prices are not an "estimate on the future of the underlying's market" at all. Furthermore "better model" needs to be decided in view of its application. If you want to trade and your model is "off the market" you are very likely in trouble since people might be able to make a riskless profit from you.
May
6
comment Empirical copula
No, the joint distribution is not defined (or only up to $Y\leq 2$) thus the copula is not defined. Of course you could extrapolate. But to do this you need additional assumptions, such as a parametric copula or joint distribution.
May
6
answered Empirical copula
Mar
3
comment The concept of an incomplete market
@Probilitator: This is a link only reply, which are supposed to be provided in comments as per policy. I learned this the hard way :-) i.e. one of my answers got removed.