Recent content by Thumama

What if the price moves randomly at all levels of frequency! A modified version of the variance ratio test can be used to simultanously test the randomness at different frequencies. As a matter of fact, studies have shown that stocks' prices exhibit randomness at different levels. As you...

Since you're asking about the future, no one will tell you the exact truth. And if, by chance, someone tells you the truth, you will never know that it is true until you see it happening. Cutten's advice, though, is the best I've read so far in this thread, IMO.

I must admit that the original post was based on an idea that is IMPOSSSIBLE to implement. It is possible to extend a random time series to become a nonrandom. It is impossible to extend a nonrandom time series to become a random time series. I thought it's possible. Sorry.. :(

Thanks for your post piezoe.. In a typical variance ratio test, we are testing the following: Var(x) = k * Var(y) Where length of period x = k * length of period y. There are different ways to improve the power of this basic test (for example: multiple VR test). I am not really sure that...

On Friday 8-8-2008, the VIX index closed at 20.66 1. There is a high chance that next Monday it will close around this number ( for example, between 19 and 22 ). Does that help you to make any abnormal profit? I don't think so. This is called level autocorrelation (significant in this case)...

The level of IV is definitely autocorrelated, but that's not important and not even relevant. What's really important is whether the IV rate of changes is significantly autocorrelated. Sadly enough, market efficiency strikes again and forced the latter autocorrelation to be economically...

dtrader98 Sorry if my statement was not clear.. English is NOT my first language :( My proposed idea is based on the assumption that returns (with different time frames) follow a random walk process ( VR=1 ) What I meant is to add data points (future returns) to the time series so that...

Still working on it.. Do you have any thought? Finding the right solution to a specific problem is easier than finding the right problem to a specific solution.. 1 + 1 = ??? <-------- one outcome ??? = 2 <-------- unlimited ways Using a simulation technique might help.

1. Market behavior is mathematically not random but economically random.. and you cannot consistently achieve abnormal returns from the mathematically predicted market 2. We perceive market behavior as being unpredictable. The cause of this perception is that we always have a limited set of...

Couldn't agree more except for the trick. Testing randomness must cover the whole time-series. Slicing the series into predetermined parts will surely produce trends and lead to the rejection of randomness. The questions are where do you make the cut and what's the length of each part...

The idea I'm thinking about is not related to Shannon's method. As to Shannon method itself; which is older than me, If it works we would have some Shannon_based billionaires by now.

Correlation has nothing to do with randomness. High correlation doesn't imply nonrandomness. Autocorrelation does. The randomness I'm refering to examines the degree of relationship between serial (not parallel) moves. Thumama..

Hi.. Assume that the market is efficient and that prices move randomly. 1. For any stock, test the randomness of its price moves. There are many tests for randomness: for example, use the variance ratio test. 2. If the value of the variance ratio test indicates a nonrandom behavior of...

Hi.. Assume that the market is efficient and that prices move randomly. 1. For any stock, test the randomness of its price moves. There are many tests for randomness: for example, use the variance ratio test. 2. If the value of the variance ratio test indicates a nonrandom behavior of...