meta user
network profile
| bio | website | researchgate.net/profile/… |
|---|---|---|
| location | Vienna | |
| age | 31 | |
| visits | member for | 11 months |
| seen | May 14 at 7:53 | |
| stats | profile views | 130 |
Risk Manager at Raiffeisen Capital Management
External Lecturer at Vienna University of Technology
|
Apr 16 |
answered | How are option expiration dates decided? |
|
Apr 15 |
comment |
Data Synchronization The Kalman filter is a general framework and the HP-filter can be described by means of the Kalman filter (pls. look into my link). Concerning before/after modeling: the filter "is" the model. The filter gives you a model for the trend. |
|
Apr 10 |
comment |
Value at Risk Monte-Carlo using Generalized Pareto Distribution(GPD) dependence (at a first step: a covariance matrix) is more important in mm than fat tails ... for a portfolio. |
|
Apr 9 |
comment |
Value at Risk Monte-Carlo using Generalized Pareto Distribution(GPD) Hi, I added a link and the formula taken from wikipedia for the random number generation of GPD. If you have fitted the parameters then you just generated uniforms and apply this formula. But if you model fat tails then you probably want to model dependencies in your model as well. If equities fall/rise then bonds or currencies are usually not unaffected. Modelling dependencies is crucial in the portfolio context. |
|
Apr 9 |
revised |
Value at Risk Monte-Carlo using Generalized Pareto Distribution(GPD) Added MC generation for GPD |
|
Apr 9 |
comment |
Value at Risk Monte-Carlo using Generalized Pareto Distribution(GPD) @purnendumaity What do you mean by "Investment Performance Risk Analytics"? If you mean something like an ex-post risk analysis (what has happened in the past) then I think you don't have to model fat tails per-se. If you look backwards then you describe what has happened. But you do MC so you model risk ex-ante - meaning what will/can happen - right? |
|
Apr 8 |
comment |
Fitting distributions to financial data using volatility model to estimate VaR Yes, if you model losses - correct. Take care when fitting the t-distribution variance ( $\nu/(\nu-2)$ is the factor for the variance, not the standard deviation). |
|
Apr 8 |
answered | Regression with Lagged variables |
|
Apr 8 |
answered | Value at Risk Monte-Carlo using Generalized Pareto Distribution(GPD) |
|
Apr 8 |
comment |
Fitting distributions to financial data using volatility model to estimate VaR I think the question is a bit too long - maybe you ca split it up. I hesitate to answer because it is too long (and my answer probably incomplete). |
|
Apr 8 |
comment |
Fitting distributions to financial data using volatility model to estimate VaR When you match an estimate of $\sigma$ and the parameter of the t-distribution then be sure to use it for variance (and not volatility) - or take the square-root of $(\nu-2)/\nu$. |
|
Apr 8 |
comment |
Fitting distributions to financial data using volatility model to estimate VaR Up to where you write "First of all, is this correct?" - I'd say yes with 2 remarks: In the code you use the $0.975$ quantile. This number is positive. But if you use the formula $VaR = \mu + q_z \sigma$ then you need the $0.025$ quantile or in the case of a symmetric distribution you just put a minus sign. Furthermore, what I do is $quantile = q_z \sigma$ and $VaR = -q_z$ and then $VaR$ is a positive number (the risk is positive and the loss is negative). |
|
Apr 5 |
revised |
Stochastic modelling of derivatives on dividends deleted 127 characters in body |
|
Apr 5 |
comment |
Stochastic modelling of derivatives on dividends one thing I have to admit: the link by JPM deals too much with stocks+dividends and not derivatives on dividends alone. I will delete the link and replace it later. |
|
Apr 4 |
comment |
Stochastic modelling of derivatives on dividends If I apply this scheme to a dividend process then it would mean that dividends pay dividends ... I can hardly imagine this. So this is off-topic - sorry. |
|
Apr 4 |
comment |
Stochastic modelling of derivatives on dividends sorry, but this is binomial pricing ... this does not directly help with futures on dividends what my question is about. I hope for a more specific answer to the question. Thanks for posting but this is too basic and too little related to my question. |
|
Apr 4 |
comment |
Data Synchronization I don't keep my promise, one more comment: you are right, that the calibration of $VAR(1)$ is more intuitive (it cna be done by a regression) than the calibration of $VMA(1)$. Our experiments in this context gave good results for the calibration of $VMA(1)$ too. |
|
Apr 4 |
comment |
Obtaining a consistent covariance matrix for stochastic volatility processes Very good question! |
|
Apr 4 |
answered | Obtaining a consistent covariance matrix for stochastic volatility processes |
|
Apr 4 |
comment |
Data Synchronization Just one more and last comment: if you look at the preprint above page 5 formula 1.6 then you see how the regression of returns on lagged returns is represented. This looks at first glance like $VAR(1)$ but when you analyze the residual then this can not be shown to be White Noise, which it should be for $VAR(1)$. |
