24 reputation
6
bio website
location Ann Arbor, MI
age
visits member for 1 year, 11 months
seen Jul 9 '13 at 23:13

Jul
7
comment Is there a name for, or any research on, a system where you try to predict future price by finding a similar price history in the past?
To view an aggregate pattern for a given time of day use cyclostationarity. en.wikipedia.org/wiki/Cyclostationarity
Jul
6
comment Risk prediction based on financial statements
RMS-Z cmbi.kun.nl/mcsis/richardn/RMS-Z.html and A NOTE ON STANDARD DEVIATION AND RMS user.gs.rmit.edu.au/rod/files/publications/St_dev.pdf
Jul
1
comment Why is the Drawdown measure not used for portfolio optimization?
Drawdown Measure in Portfolio Optimization June 25, 2003 papers.ssrn.com/sol3/papers.cfm?abstract_id=544742 Portfolio Optimization with Drawdown Constraints April 8, 2000 papers.ssrn.com/sol3/papers.cfm?abstract_id=223323 DRAWDOWN MEASURE IN PORTFOLIO OPTIMIZATION Accepted 25 May 2004 ise.ufl.edu/uryasev/files/2011/11/IJTAF_DrawDown_Paper.pdf PORTFOLIO OPTIMIZATION WITH DRAWDOWN CONSTRAINTS January 13, 2003 ise.ufl.edu/uryasev/files/2011/11/drawdown.pdf
Apr
2
comment Data Synchronization
Time scale transformations olsen.ch/fileadmin/Publications/Working_Papers/… If this fits your needs, Olsen has a few more papers on this topic.
Mar
15
comment Reasoning behind multiple names for the equivalent risk measures AVaR/ETL/ES/CVaR
Possibly the biggest road block to learning statistics are the varied and nonsensical naming. “[...]bad names reflect (or even result in) difficulties in understanding.” Hurst, Joseph, colours and noises: The importance of names in an important natural behaviour, Demetris Koutsoyiannis itia.ntua.gr/getfile/792/1/documents/…
Mar
11
comment Square root of time
“without a change of model”, I agree, and a simple example would be to change your scale to a 10 day bar + a probability weight. “P. Samuelson and it is the fact that the best forecast for the future price of an asset is its present price”. Analysis of short term price trends in daily stock-market index data. arxiv.org/pdf/1211.3060v1.pdf
Mar
11
comment Predict Market Direction, What is forecastable/unforecastable?
Long range dependence in financial markets, by Rama Cont. By contrast, the autocorrelation function of absolute returns remains positive over lags of several weeks and decays slowly to zero. proba.jussieu.fr/pageperso/ramacont/papers/FE05.pdf, Long memory in return structures from developed markets, 2012, Sharad Nath Bhattacharya, MouSuMi Bhattacharya. ehu.es/cuadernosdegestion/documentos/110312sb.pdf
Mar
11
comment Square root of time
Who is less wrong? Using 1% daily returns, over h = 10 days. 2.99% Goldstein/Taleb, 3.16% Dibold/Hickman/Inoue/Schuermann. We Don't Quite Know What We are Talking About When We Talk About Volatility papers.ssrn.com/sol3/papers.cfm?abstract_id=970480
Mar
6
comment How to perform Empirical Mode Decomposition?
There is inherent massive lag in the calculation of the Hurst exponent (H), maybe this is your problem? How are you using EMD in your strategy, what method of EMD are you using, do you plan to use EMD in real time? FYI: I'm in the process of reinventing IMF part of the EMD method, specifically for capitalized markets for real time use.
Dec
30
comment Fastest algorithm for calculating retrospective maximum drawdown
Your question is not clear to me. Do you mean the easiest technique to code, or code that is CPU efficient?
Dec
24
comment What are the best Journals & Conferences in Quantitative Finance?
@vanguard2k, en.wikipedia.org/wiki/ViXra
Dec
20
comment Monty Hall Model
arxiv.org/pdf/quant-ph/0202120.pdf The Quantum Monty Hall Problem, arxiv.org/pdf/quant-ph/0109035v3.pdf Quantum version of the Monty Hall problem
Dec
20
comment What are the best Journals & Conferences in Quantitative Finance?
link , viXra.org
Dec
10
comment Monty Hall Model
3 days vs. 3 choices of the market direction plus market moving news, I don't think this is the same problem as what the Monty Hall problem is about. Monty hall only had 2 rewards a goat and a car, and 3 doors to choose from. I think you need to re-model the concept of what is a door, and what the 2 rewards are behind the 3 doors. I think you need to eliminate the flat position, and you only need to work with one day (Tuesday), leaving you with 2 rewards (goat/car, long/short).
Dec
10
comment Monty Hall Model
Your assuming that manager A is an agent of Monty Hall (all knowing), and has exposed a goat behind door number 1, which is a long position. The flat position is not a viable option as you stated there is a breakout due on Tuesday, so you can eliminate it (but do you reassign the probability weight, and if so to what?). So you assume that long positions are goats, and you take the short position.
Nov
19
comment Proxy for a trigonometric angle function
@chrisaycock I need a function that will capture the estimation of the Hurst exponent without using the linear regression slope calculation.
Nov
19
comment Proxy for a trigonometric angle function
tks, and I was thinking that this might be the wrong forum for this Q. I don't see that I have control over deleting my post.
Nov
19
comment Proxy for a trigonometric angle function
@chrisaycock Time based financial calculation that requires a slope calculation are suspect. I'm looking for a stable/robust representation for the slope component of the slope-intercept form. Angle calculations using market data are nefarious to work with, as market compression rescales nonlinear. I'm working with the Hurst exponent, it utilizes the slope-intercept form to characterize the market.
Nov
8
comment Hurst Exponent Calculation
I just started calculating the Hurst exponent a few days ago using OpenOffice. I've been looking for examples as well to help me finish it, no luck so far. Post your study if your able, it will help me, and maybe someone can make the necessary corrections?
Nov
3
comment Can the Hurst exponent be greater than one?
Testing software to estimate the Hurst exponent can be difficult. The best way to test algorithms to estimate the Hurst exponent is to use a data set that has a known Hurst exponent value. Such a data set is frequently referred to as fractional brownian motion (or fractal gaussian noise). As I learned, generating fractional brownian motion data sets is a complex issue. At least as complex as estimating the Hurst exponent. bearcave.com/misl/misl_tech/wavelets/hurst/index.html