Take the 2-minute tour ×
Mathematics Stack Exchange is a question and answer site for people studying math at any level and professionals in related fields. It's 100% free, no registration required.

I have a number of probability distributions that describe a number of points. like this: prob

Now if i have draw a one point out of each distribution, i get a bunch of points randomly set on the 2-dimensional surface. How can i, given the set of probability distributions and a set of points compute the probability that i would draw something like that again? What is the correct mathematical term for what i want to compute?

share|improve this question
    
Likelihood? –  Did Jul 19 '12 at 16:26

1 Answer 1

up vote 1 down vote accepted

If I understand your question right, then what you want is to develop a statistical test.

Essentially, given some sampling of points $P = \left\{ p_1, p_2,\ldots,p_n\right\}$, you need to estimate the probability that this sampling of points resulted from some distribution. In this case, your null hypothesis is that $P$ was drawn from your presumed distribution. You will want to set a threshold for statistical significance. In other words, there is no concrete, deterministic way to distinguish between a set of points happening to randomly align with your chosen distribution by sheer luck, or whether they actually came from your distribution.

There are many such tests; a basic example is a chi-squared test. Off-hand, I don't know which test is best for your application, but the Wikipedia page should direct you to some good information.

share|improve this answer

Your Answer

 
discard

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.