What's new

Recent content by berrymucho

  1. berrymucho

    Right and left quantiles

    Is "x" a random variable or a realization of a random variable (i.e. specific point)? If the former, then the relationship you quote is always true as the distribution of x is flipped like in a mirror, looking at the distribution of random variable x' = -x. If x is a specific point in the...
  2. berrymucho

    Help [Bootstrapping]

    I think it's just a typo in post #3 above. The first maturity is 0.25 year (3 months), not 0.025. So ln(100/97.50)/0.25 = 10.127%.
  3. berrymucho

    FAQ After Exam ARPM (Advanced Risk and Portfolio Management) certificate

    See my post above for a rough estimate of difficulty judging by concepts. Also it’s worth checking his textbook (downloadable for free) to gauge your level of comfort. In addition to concepts the certification emphasizes hands-on coding. Any mathematical background is recommended.
  4. berrymucho

    Win prizes for forum participation!!

    Hi @Nicole Seaman! Cool, thank you very much for the prize! Glad to be of help. I'll get the Amazon gift card please. And congratulations on passing the 50,000 forum members mark this week...! -berrymucho
  5. berrymucho

    Current Issues section

    You’re supposed to download the series of articles constituting the Current Issues (“part 5”) on your own directly from the GARP website. You’ll find practice questions for this part specifically if you subscribed with a preparation provider.
  6. berrymucho

    FRM and ERP benchmarked against international qualification standards

    I wanted to share this pointer I received from GARP last week, as a morale booster for everyone hard at work and also as a motivation for aspiring candidates. In short, this study commissioned by GARP concludes that the FRM certification is comparable to a Master's degree in major education...
  7. berrymucho

    P1.T2.80.1 Confidence Intervals

    I don't know the details of the specific example you're referring to so let me assume a normal distribution instead of a t-distribution with the appropriate degrees of freedom (as you know they get close after ~30 data points). A t-stat = (x_hat-mu)/s_x_hat = 0.54 indicates that the estimated...
  8. berrymucho

    Exam Feedback November 2017 Part 2 Exam Feedback

    The certificate itself is standard US Letter size, 11 in x 8.5 in. It comes in a folding cover that is 12 in x 9.5 in. Get ready...
  9. berrymucho

    P1.T2.80.1 Confidence Intervals

    Say for testing a true mean greater than a value of mu, the null hypothesis you're seeking to reject is H0: mean < mu, or equivalently, H0: mean-mu < 0. That is, you want to use the lookup table for a single sided test. One-sided testing is for "greater/lower than" questions, two-sided testing...
  10. berrymucho

    FRM versus CFA

    Thanks for the update on this question. As to the level of infrastructure/development of the FRM program — in particular the books being a collection of textbook chapters and articles — I like to think of it as part of "what it takes" (the mystique) to get the FRM certification. It certainly...
  11. berrymucho

    Exam Feedback November 2017 Part 2 Exam Feedback

    Thanks. Interesting, 2nd lowest pass rates for both part I and II since the split in 2010...
  12. berrymucho

    FAQ After Exam ARPM (Advanced Risk and Portfolio Management) certificate

    For context, I attended the ARPM Bootcamp in 2015: 6 days, 8am-6pm intensive course + practice sessions. I did not take the certificate. I don't think there's yet a demand/recognition specifically for the ARPM certificate but from the development I've seen in the past couple of years, the...
  13. berrymucho

    Exam Feedback November 2017 Part 2 Exam Feedback

    There might be some reporting bias... not everyone is comfortable talking about their experience, or just simply don't remember the details as clearly. And seeing a group of peers agreeing on their answers might even be less of an incentive to share that you got a different answer. However, the...
  14. berrymucho


    Not sure whether the slides appeared back-to-back in the original material, both are correct, but the notation is different. If you pay attention in slide 1 the bivariate correlated variables are E1 and E2, with Z1 and Z2 the univariate independent random variables, where the letter Z is...
  15. berrymucho

    Multiple Regression Coefficient Testing (garp16-p1-09)

    The F-stat is the appropriate one to test the null hypothesis that all variables are =0 simultaneously, the alternative being that at least one variable is not null. Using the t-stat for each variable in turn would be too loose: for 2 variables at 95% level individually, the chance of having at...