Ryogi

1,837 reputation

619

bio	website
	location
	age
visits	member for	1 year, 8 months
	seen	19 hours ago
stats	profile views	167

	1,837 reputation	bio	website		visits	member for	1 year, 8 months
619 badges		location			seen	19 hours ago

summary answers questions tags badges favorites bounties reputation activity

70 Comments

suggestions reviews revisions comments badges posts accepts all

Apr 5	comment	Using variance ratios to test for mean reversion I updated my answer to address some of your comments.
Mar 30	comment	From a high frequency point of view, with a price prediction and assuming infinite leverage, how do you determine optimal trade size? @CharlesM, as I mentioned in the second point, a good starting point is the work by Obizhaeva and Wang. Following on the papers that cite it (e.g. on google scholar) will give you an idea of where the literature is at.
Feb 19	comment	Recover full tick data from missing tick data While interpolation can be useful at medium frequencies, it is hardly useful at the tick level. Arguably most of the information is contained in the fact that the "tick" happened ...
Feb 14	comment	What data sources are available online? Any idea on the cost of access for academic users?
Feb 5	comment	Testing for stationarity in large sample sizes All you need is to spend more time getting familiar with the definition of stationary process with some examples and counterexamples. It is standard material in any time series analysis book.
Feb 5	comment	Testing for stationarity in large sample sizes On splitted data the tests will not reject the hypothesis, as long as the sample size is not too small.
Feb 2	comment	How do you estimate the capacity of a strategy from historical data? +1, good question. Can you expand on why standard market impact modeling (such as that described here) is not adequate? It seems to me that the modeling tools would be the same, and what would change is instead the maximization problem implied by the strategy (in contrast with the simpler "execute a large block").
Nov 26	comment	How do I estimate the parameters of an MA(q) process? In my opinion, it is too elementary to be on topic. Every textbook on time series analysis covers this.
Nov 16	comment	Does mean reverting imply mean stationary? Mean stationary means that $E(x_t) = E(x_s)$ for all $s$ and $t$.
Nov 12	comment	Measuring liquidity Exactly, lack of consensus.
Nov 12	comment	Measuring liquidity It sure makes for an interesting read. As to referring to highly respected (which they are) to hint at correct and valuable, you lost me at the 'hi'(gly). Here is a differing viewpoint.
Nov 7	comment	Measuring liquidity I'd be cautious about trusting VPIN. There is nothing like a consensus on its validity or robustness.
Oct 30	comment	Sources of Machine Readable News @pyCthon, yep, most answers to the questions on this site can be found on through google or google-scholar. But a good answer doesn't require you to sift through all that info.
Oct 29	comment	Sources of Machine Readable News Examples of such companies?
Oct 29	comment	Using alpha to evaluate trading strategy Whether is matters or not depends on what question are you interested in answering using this model.
Oct 29	comment	forward- and backward adjusting stockprices Maybe you should try do describe an example in full detail. In doing so, edit your own question instead of adding a comment.
Oct 22	comment	Connections between random walk and heat equation (Material for ~) Einstein's derivation of the diffusion equation is really intuitive. I can't find a good ref right now...
Oct 16	comment	Are two identical time series cointegrated? No, using vs not-using qualifiers in a technical discussion is not an objective thing.
Oct 16	comment	Are two identical time series cointegrated? More importantly, since the cointegrating linear combination in this case requires $\alpha = -\beta$, the conclusion that $(\alpha + \beta) X$ must be stationary does not lead to any contradiction as $\alpha + \beta$ equals zero and $X$ could be anything.
Oct 16	comment	Are two identical time series cointegrated? You didn't use any quantifier in the original answer. That's wrong. Using some is acceptable. A mathematical text would state that there exist $\alpha$ and $\beta$ such that $\alpha X + \beta Y$ is stationary.