My question is probably worded incorrectly but here it is: I have (say) 3 discrete random variables: x1: has 15 levels (uniform pdf for simplicity) x2: has 3 levels (uniforms) x3: has 4 levels (uniform)
I want to generate n samples in such a way that:
- there are no repetitions of samples
- as n --> 15x3x4 the entire "full factorial" sample is generated;
- When generating (n+d) set of samples, the first n samples are the identical for any d
I tried to use Sobol quasi random sequence to generate this sample BUT I am not able to satisfy #1 above without retaining all prior points in memory and checking for duplicates. This is something I would like to avoid.
Thanks for your answers.
1 Answer 1
if i have understood your question, then you might find my blog post on "how to do quasirandom fractional multi factorial sampling based on the sobol sequence." useful.
http://extremelearning.com.au/a-probabilistic-approach-to-fractional-factorial-design/
-
$\begingroup$ Welcome to the site. We are trying to build a permanent repository of high-quality statistical information in the form of questions & answers. Thus, we're wary of link-only answers, due to linkrot. Can you post a full citation & a summary of the information at the link, in case it goes dead? $\endgroup$2021年01月16日 15:59:42 +00:00Commented Jan 16, 2021 at 15:59
Explore related questions
See similar questions with these tags.