Max Li
Reputation
399
Top tag
Next privilege 500 Rep.
 Jan 20 comment Generate correlated random variables from Normal and Gamma distributions from these 3 steps, they are correlated with the desired correlation matrix after the 2nd step, but not after the final 3rd step. correct me if I'm wrong Jan 16 comment Generate correlated random variables from Normal and Gamma distributions can you elaborate on "and then generate the random variates"? Do you generate k normals and m gammas and the put it into a copula? Jan 13 comment Generate correlated random variables from Normal and Gamma distributions Assume that this mixture of distribution is given and I can't escape into log-normal and to some extent tolerant towards negative values. Simulating into positive quadrant with given covariance is also interesting, thanks for this! Feb 8 comment How to minimize the difference between a parametric VaR and a MC-VaR with lognormal assumption? @AdAbsurdum True, for multivariate case it doesn't work Feb 7 comment Where can I find data on the interbank lending market? @JoshuaUlrich If you think that my question is out of scope, feel free to close it, I actually thought it might be on the edge. No, I didn't contact anyone, I thought to try at first to find freely downloadable data Feb 7 comment Where can I find data on the interbank lending market? @JoshuaUlrich I've read the topic you mentioned before posting my question. I'm actually asking for a very specific data (lendings bank-to-bank), I didn't find it in neither that topic, nor through google, nor in papers). Feb 4 comment Maximization of CARA utility function: unique solution with an unbounded parameter? Of course the exact solution depends on the pdf assumption, but if we assume that pdf is continuous, then utility function will be also continuous. Then we can use an analogue of extreme value theorem (continuous, bounded from above and closed from right), which states that a maximum does exist. Feb 4 comment Maximization of CARA utility function: unique solution with an unbounded parameter? @AlexeyKalmykov "you need a budget constraint here for a, otherwise your optimization problem makes no sense" - if $a>w_0$ you can think of it as if the consumer borrows $a-w_0$ at $r_f$ rate, i.e. it can make sense. Feb 2 comment Home/hobbyist quant trading - possible to profitable or just an intellectual hobby? @JoshuaUlrich with "amateur traders" I meant "non-institutional traders", i.e. not necessarily unskilled traders, sorry for being not enough precise. I agree that the question was formulated unprofessionally, and if 4 people voted to close it down, then I'm ok with it. Feb 1 comment Home/hobbyist quant trading - possible to profitable or just an intellectual hobby? I wouldn't see it as a complete off topic. Comparing with institutional investors, amateur traders have another working framework: they have essential transaction costs, they are more risk-averse etc. i.e. there are some theoretical questions behind to be answered (for instance, how does mean-variance portfolio strategy looks like under transaction costs restriction)