khaled Posted January 31, 2012 Posted January 31, 2012 Greetings, I'm working on a project where Stocks data are managed in order to be analyzed for an investor, 1. what statistical distribution\s should I use for this type of data ? 2. should I only consider the final price of the stock during the day, or include more detailed variables ?
DrRocket Posted February 1, 2012 Posted February 1, 2012 Greetings, I'm working on a project where Stocks data are managed in order to be analyzed for an investor, 1. what statistical distribution\s should I use for this type of data ? 2. should I only consider the final price of the stock during the day, or include more detailed variables ? The mere fact that you are asking these questions shows that you are in WAY over your head. No one has any particularly effective trading models of the stock market, or if they do they are not talking. Modern high-frequency traders use models that consider the stock price a millisecond ago, and they do not alway make money -- sometimes they lose quite a bit. There are some models used in the bond market that are effective for large trading houses. They have groups typically staffed by PhD ex-particle physicists and/or algebraic geometers working full-time on sophisticated models. But even these guys don't try to predict the stock market over any significant length of tiime. If you are going to pursue this sort of thing seriously you need to really learn the theory of stochastic proceses and the associated calculus. When you understand both the Ito integral and the Stratonovic integral you will be almost prepared. Until then you might as well skip the middleman and just send your money to Goldman Sachs. Or go to Vegas and have some fun while you lose your money. 2
khaled Posted February 1, 2012 Author Posted February 1, 2012 If you are going to pursue this sort of thing seriously you need to really learn the theory of stochastic proceses and the associated calculus. I had a class on Probability & Statistics, and another on Simulation & Modeling. When you understand both the Ito integral and the Stratonovic integral you will be almost prepared. So I need to learn these integrals, and what else should I learn in order to be able to build a model ? Until then you might as well skip the middleman and just send your money to Goldman Sachs. Or go to Vegas and have some fun while you lose your money. Actually, I'm writing a software for my father, my father wants simple functionality which will be considered in the first version. The software is simple it keeps stocks price data, but I want to add more analysis functionalities to the software.
ewmon Posted February 1, 2012 Posted February 1, 2012 You can begin with educational documents like this one written by the NASDAQ, and head toward material on the statistical mechanics of stock markets. 1
khaled Posted February 1, 2012 Author Posted February 1, 2012 (edited) It seem that Statistical Mechanics of Stock Markets are modeled using Mathematical Physics Models, I know mathematics and physics, but what is mathematical physics ? Edited February 1, 2012 by khaled
ewmon Posted February 2, 2012 Posted February 2, 2012 (edited) I think you're slightly off track. The first sentence of the Wikipedia article on Statistical mechanics reads: Statistical mechanics or statistical thermodynamics is a branch of physics that applies probability theory, which contains mathematical tools for dealing with large populations, to the study of the thermodynamic behavior of systems composed of a large number of particles. So there you have it. Stock markets are systems composed of a large number of stocks, and you're interested in developing mathematical tools that use probability theory in order to study the dynamic behavior of these systems. Edited February 2, 2012 by ewmon 1
Recommended Posts
Create an account or sign in to comment
You need to be a member in order to leave a comment
Create an account
Sign up for a new account in our community. It's easy!
Register a new accountSign in
Already have an account? Sign in here.
Sign In Now