A new book is available on the topic: Market Microstructure in Practice.

We mainly used Matlab, and python (matplotlib) for few of them.

<t>I guess the publisher will put an extract on amazon or on its web site soon.if you can't wait here is the table of contents emacs produces from the tex sources: 1 Monitoring the fragmentation at any scale 1.1 Fluctuations of market shares: a first graph on liquidity 1.1.1 The market share: a not ...

A new book on market microstructure is available: "Market Microstructure in Practice (Lehalle and Laruelle Eds)"any comment is welcome.

<t>Quote--Which curves are you referring to?bins of around 5 minutes, if you compute the volumes (sum them) or the volatility (which estimator do you use?) you will obtain curves.Now it seems that you would like a model of the intra day seasonnality of these cures?Quote--Are you saying that the acti...

<t>be careful on how you plan to use the curves.for instance volumes "slices" are far more iid than volatility trajectories.for volume any usual seasonality methodology will work, for volatility, think about an ornstein uhlenbeck with a time-varying "mean"i.e. in m_t is time varying and not constant...

<r>Here is an interesting paper to begin this kind of analysis:<URL url="http://papers.ssrn.com/sol3/papers.cfm?abstract_id=1712822"><LINK_TEXT text="http://papers.ssrn.com/sol3/papers.cfm? ... id=1712822">http://papers.ssrn.com/sol3/papers.cfm?abstract_id=1712822</LINK_TEXT></URL>(the theoretical a...

<t>usual biblio:- Bouchaud, Almgren, or the nice review by Gatheral to be able to build nice models for liquidity capturing/providing- Almgren, Lehalle, Avellaneda&Stoikov to use such models for trading- Pagès,Laruelle&Lehalle to simultaneously estimate and optimize trading in a dark pool co...

<t>two main points:1. you should not use the "usual calculation" for intraday vol estimation, especially if you sample at a rate lower than 5min (for less liquid stock, you should use another estimate below 30min bins), look at Zang+Mykland+Ait-Sahalia or Jacod, or Rosenbaum+Robert papers2. anyway y...

<r>two ways:1. under certain assumptions you know the theoretical distribution of correl coef estimates, you will probably end with a Fisher-like test for the comparison (to simplify your calculus, test your C_cond against the estimate on the 900 other poins)2. bootstrap (the lazy way):sample your 1...

<t>This is an actual and interesting question.In a liquid market the "liquidity providers" as you define them will mainly be market makers, read the paper of avellaneda & stoikov on that and you will have a quant view of the famous bid-ask-spread vs volatility paradigm. It will provide you some ...

read papers on market impact (authors: Bouchaud or Almgren to begin)

read papers on market impct (authors: Bouchaud or Almgren to begin)

<r>Jean Jacod was the first to work on the "rounding effect" (in a book in memoriam of Paul-André Meyer, I think), then he worked with Delattre on this topic. His last paper joint with Ait Sahalia is really fine.Neil Shephard worked also on the subject. see also Rosenbaum & Robert "A new approac...

any textbook in statistics will give you formula to test such hypothesis...