405 reputation
39
bio website
location
age
visits member for 2 years, 10 months
seen Nov 25 at 19:14

Nov
25
comment Switching from C++ to R - limitations/applications
try Julia julialang.org
Nov
18
comment How to estimate the following model?
I would draw attention, that in many situations, just "fitting" (not "estimating") model is needed. Fitting in the sense that we won't need to obtain variance of parameters and so their p-values. Minimization of MSE is enought and is straightforward even in the case of family of GARCH model (but computationally demanding and multiple restarts are needed to make sure), MSE is ok, as it is M-estimator. After fitting model we can check its predictive power and goodness of fitness to train date, to get first glimpse about its usefullness. Its like fast prototyping.
Mar
5
comment Toy models of asset returns
en.wikipedia.org/wiki/Agent-Based_Computational_Economics , and suitable process which generates density with excesse kurtosis could be obtain by sum of a random number of i.i.d. Gaussians - sum of random number of trades each trade moves price iid Gaussian, number of trades is random and arise from interaction between agents - I've seen a few such papers; for general overview of agent models in quantitative finanse you could check this survey hal.archives-ouvertes.fr/docs/00/62/10/59/PDF/reviewII.pdf ps. zero intelligence models are easier = starting point
Feb
16
comment Problems with dealing with GARCH models and intra-day data
I didn't use fGarch because this implementation of garch does not support external variables and I haven't been aware of existance of rugarch package
Feb
16
comment Problems with dealing with GARCH models and intra-day data
but AFRIMA which also have property of long memory didn't work - $d$ was statistically insignificant
Jan
23
comment Are there any derivatives which pay amount $a(p-b)^{2}-c$ where $p$ is the price of underling asset?
@Brian B very interesting, thanks
Jun
20
comment Is a linear combination of GARCH processes also a GARCH process?
good answer, but usually we work with logarithmic returns, if 'x1' and'x2' are returns and x3=a1*x1+a2*x2, and r1=ln(x1),r2=ln(x2), r3=ln(x3) then r3 isn't equal to r1+r2
May
22
comment Has high frequency trading (HFT) been a net benefit or cost to society?
but the volume you can trade at bid and ask is lower than in pre-HFT times
May
22
comment What is a commonly accepted econometric model for volume?
@Dirk Eddelbuettel but AR(1)-GARCH(1,1) does
May
21
comment How to model time series of illiquid stocks - 400 observations (transactions) per 8 hours?
Ok, I'm going to add more details in next two days (from the statistical and econometric side).
Apr
26
comment Does the correlation amongst stocks rise when stock values decline?
I believe I've read that unconditional correlation increases also.
Apr
26
comment How do I graphically represent the evolution of a covariance matrix over time?
This appoach could be use if we first make cluster analysis, and then make minimum spanning tree for cluster centres. Beyond that change in spanning tree structure could be view as evidence of some "topological" changes in market structure.
Apr
26
comment Why do high frequency traders use rapidly cancelled limit orders?
+1 how lagging by targeted quote-stuffing create arb to opportunities ? and where could I read about "mapping the topology of the exchange servers" by quote-staffing ? this is very interesting
Apr
26
comment Why in general is the variance of volume changes higher than variance of price changes?
@babelproofreader that is good question
Apr
26
comment Why in general is the variance of volume changes higher than variance of price changes?
Could you write more about it, are there any research about shape of function f(x) that : (delta_Price)^2=f(delta_Volume) ? local depth of the market have to be accounted somehow
Apr
24
comment How to quickly estimate a lower bound on correlation for a large number of stocks?
What is the upper bound on that correlation ?
Feb
12
comment Measuring liquidity
Do you know any details of making of that chart od Nanex - is each colour a percentage of depth for given price level ? or mayby it's depth measured by quantity of assets ?