Mathematics Stack Exchange is a question and answer site for people studying math at any level and professionals in related fields. Join them; it only takes a minute:

Sign up
Here's how it works:
  1. Anybody can ask a question
  2. Anybody can answer
  3. The best answers are voted up and rise to the top

Let me change my question:

I have a sequence of 512 numbers (these 512 numbers can have a value between 0 and 255) (in computer mode these numbers can be between 00000000 and 11111111 (bits)). For these 512 numbers I calculate the average value, standard deviation value and kurtosis value. Now I want to calculate the values for the distribution of averages, distribution of standard deviations and distribution of Byte values. Finaly, I want to compare the distributions from other sequesces of 512 numbers to find out the similarity (as percentage) that two sequences have. I dont understand how can I calculate these distributions.

for example Distribution of Averages is : the probability that an average chosen from all the averages of a memory block is of value B in the range of 0-255.

Dxb=Pr((B+1))>Xj>=B ,Xj=Average.

share|cite|improve this question
To check I understand your question: you have two sequences of 512 bytes, call them $X$ and $Y$, and you want a measure of how similar they are? – Chris Taylor May 19 '11 at 10:41
yes exactly! i want to have a percent of their similarity. for example that sequences X and Y are 78% similar. – nomercy May 19 '11 at 10:46
To say that 'sequences X and Y are 78%' similar, in this approach, makes no sense to me. Before asking "how to calculate" something, you must be clear what results you expect. Say X and Y have the same values in distinct order- are they 100% similar? Say $x_i = y_i+1$ : the have same variance and higher centered moments, and similar average (difference =1) How similar would you call them? – leonbloy Jun 24 '11 at 14:06

For the new question, it appears that you have no problem calculating the mean, standard deviation, and kurtosis of one series. Then if you have a bunch of series and want to calculated the distribution of means you do it the same way. You have data that comes as $(i,mean_i,sd_i,kurt_i)$ and ignore where it came from. So you can calculate the mean and standard deviation of all the means. As you have not defined "the similarity as percentage" I don't know what to do with that.

share|cite|improve this answer

Your Answer


By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.