Reputation
6,938
Next tag badge:
34/100 score
13/20 answers
Badges
13 41
Impact
~154k people reached

Apr
18
revised Backesting VaR on overlapping intervals to year's end
edited body
Apr
18
asked Backesting VaR on overlapping intervals to year's end
Apr
14
comment How to price a stock under Q and stochastic interest rates?
Using the measure Q you can not predict the future. Applying cost-of-carry (see google for details) you get the correct price for a forward that prevents arbitrage. Noone knows the future. But we an price to avoid arbitrage ...you don't price a stock - it already has a price when traded. But you can price a forward. And you don't have to have any clue about the future .. you just need an arbitrag free price..
Apr
13
answered hedge a USD index into EUR
Apr
12
comment When and how to use RNN for stock analysis or trading
Hi, whatever model: you want to train on 10 years of data and predict one day? Trainin on SPY and predict Google (Alphabet)? You even want to predict an uncorrelated price? How should this be possible with reasonable accuracy?
Apr
11
comment How to price a stock under Q and stochastic interest rates?
Hi, the argument that bond prices are real-world observations does not count. They are prices. Whenever you fit a process to match prices then you work under Q, the pricing measure (aka risk neutral). This means whatever you think of the future (P-measure) you take expectations that match prices.
Apr
9
answered How to create time series with lagged in R
Apr
9
comment How to create time series with lagged in R
did you have a look at the function "lag" ? Furthermore this is at most a question for stackoverflow ...
Apr
8
revised Trinomial model converges to Black-Scholes weakly
edited title
Apr
7
answered How to price a stock under Q and stochastic interest rates?
Apr
7
answered Why is convexity adjustment applied to swap price for a nonstandard swap, in simple terms?
Apr
7
comment What is the name of all 1-day movements, 2-day movements etc
To see that returns can have correlation zero but be dependent think of $X,Y,Z>0$ independent, then $X/Z$ and $X/Y$ are uncorrelated but not independent as both are scaled by $Z$.
Apr
7
comment What is the name of all 1-day movements, 2-day movements etc
Hi, I am not Richard Hardy, my username ist just Richard. No, I would have to think a bit more about Heston here. But we speak of realized returns - right? So not risk neutral, just statistical. If their square shows autocorrelation, then they can not be independent. The square is related to volatility (as a formula and in intuition, if you think that sign does not matter but size). If returns were normal then correlation zero and independence are equivalent. For example a multivariate t-distributuion can have correlation zero but dependence.
Apr
6
comment What is the name of all 1-day movements, 2-day movements etc
The title of the question is a bit misleading ...
Apr
6
answered What is the name of all 1-day movements, 2-day movements etc
Mar
30
comment simulating from the CIR++
What is $\phi(t)$ ?
Mar
30
comment Which are useful applications of clustering in quantitative finance?
thanks, I am following his RSS feed from now on ;)
Mar
30
revised Sensitivity of short-term vs long term options' IV
added 19 characters in body
Mar
29
comment Square of arithmetic brownian motion process
Very good answer!
Mar
26
comment Real world application of stochastic portfolio theory
@John You are right about the paper mentioned above .. I think they lack a lot of important info (vola, draw down, Sharpe ratio, rolling performance, TE, ...) that I would be interested in ... and all the SC and turnover issues are missing too.