Search results

Hi Brian, I think you are right in that there is no risk if you hold the two notes to the end. As a reason to care about NPV differences in between, I can think of: - you might be required to hold capital according to the VaR of your position and the VaR is not zero. - you might get in trouble...

Here it makes sense to differentiate between an estimator and a sequence of estimators. Often this distinction is very murky. For example Theta_n (X) = 1/n * (X1 + X2 + ... + Xn) is an estimator for the expected value for a fixed n. For a n = 1, 2, 3, ... We get an infinite sequence of...

Sorry, i was unclear: Calculatimg the ES from the probabilities, like it was done in the solution to the original exercise is not historical simulation. Because you calculate from PDs and assumed distributions and not from empirical returns. But if you conduct a Monte Carlo Simulation, as I...

I guess the short answer is, this is not historical simulation. The slightly longer answer: If you would conduct a monte-carlo simulation with the above probabilities and look at the worst 5% of your simulation runs, you would find 0,04% of your runs have 2 defaults, 3,92% have 1 default. Now...

Hi Newkirk, The mathematically answer is: If you have two random variables A and B with standard deviation s(A) and s(B), than the standard deciation of the sum A+B is s(A+B) = sqrt(s(A)^2 + s(B)^2 + 2 * s(A) * s(B) * cov(A,B) ) For example consider two portfolios with A and B being the...

Passed with 1-1-1-2-1 Im very happy. I put a lot of time into it, happy it payed of. Congratulations to all the others who passed, too.

It was stated in the question that the swap was valued at par. I think that means, that the value of floating and fixed leg cancel each other out, independent of the age if the swap.

I gave the same answer, but i'm not so sure, that it is correct. Essentially you valued the fixed leg with ois discounting. Its not clear to me, why that should be the same as the floating leg. They are valued at par with libor discounting, that might be different under ois discounting, right?

Th your pass/fail only depends on your total score. No sectional cutoff.

Im not 100% sure, but i thought the whole budget was 100 Mio. And from the answers only one was below that. The others were 140 Mio. and above. So i choose the one below the total budget, because of no correlation, the seperate VaRs must be lower than portfolio VaR.

I felt something was missing from the IRS question. The 2 year swap payed 6% fix and vas valued at par. I.e. Was worth zero. The question was the value of the floating leg with ois rates 5% for first year and 5.5% for 2 years. I think you need the current libor fixing and the forward rate from...

But isnt it the same for the spread? I would pay nothing for a cds that has no value for me?

The higher the correlation the more useless the cda. There were two graphs that showed decreasing value of cds with correlation. I choose the one that eventually ended at zero, since the cds is worth nothing, if the correlation is one. At least thats true if the recovery rate is zero. I can't...

Looked like collaterilized interest rate swap (with a threshold) to me.

No, pass/fail is determined on your total score. Garp uses a secret algorithm for that that every year magically results in c.a. 45% passing for Part 1 and 55% for part 2 (+- 3%).

The only results you get from Garp besides pass/fail is the quantile for each topic. So you can be in the first, second, third or fourth quantile.

Exactly that one. I choose the first, because i thought whatever decreaes the RAROC also decreases the sharpe ratio and why 14 PCs should be necessary and 13 wouldn't be enough, was not clear to me. But that was wild guessing.

I think we all had a different numbering. But i came to the conclusion, that it was contrary to the old questions. I choose light tails as an answer and the old question if i remember correctly had heavy tails as an answer. I might be wrong though. What was your answer?

In Frankfurt we had a clock and I think its very bad that some sites don't. I would be pissed too. Also the proctor specificially said, that we can write in the booklets as much as we want to, it just won't be graded. I was surprised by the lack of calculations. Some of the topics that took a...

Shakti, thank you for your reply. The confidence level for the backtesting is in both cases 90%. But one time a 99% VaR and the other time a 95% VaR is backtestet.