Timeline for Is this correct ? (generating a Truncated-norm-multivariate-Gaussian)
Current License: CC BY-SA 3.0
13 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jun 26, 2015 at 14:52 | vote | accept | Loves Probability | ||
| Jun 23, 2015 at 17:03 | history | edited | whuber♦ | CC BY-SA 3.0 |
added 394 characters in body
|
| Jun 23, 2015 at 14:27 | comment | added | whuber♦ | Looking at the marginal distributions is the most straightforward way I could find to illustrate the differences in the procedures. I added a figure and some code to show these marginals. | |
| Jun 23, 2015 at 14:26 | history | edited | whuber♦ | CC BY-SA 3.0 |
added 1381 characters in body
|
| Jun 23, 2015 at 4:35 | comment | added | Loves Probability | Thanks for the details. I added a 2-D scatter-plot as you said and fixed a few sentences. By the way, sorry I didn't really mean to transfer the total burden of proof to you. My proposal seems to work okay with all simple checks, therefore I am curious why its wrong, which is also the main purpose of this question. | |
| Jun 22, 2015 at 17:27 | comment | added | whuber♦ | As near as I can tell, you propose drawing $X_1,\ldots,X_{n-1}$ iid from a Normal distribution and $X_n$ from a two-sided truncated Normal. That is so obviously not a truncated MVN distribution, as a scatterplot for $n=2$ will easily reveal, that I believe I have been unable to understand that part your question. More generally, the burden of questions that ask why something does not work is on the asker to provide evidence that it does work. Perhaps if you supplied such evidence, the nature of your question would become clear. | |
| Jun 22, 2015 at 16:28 | comment | added | Loves Probability | Thank you very much. But, may I also request you to answer on my first comment above? It seems, my proposal also gives a good histogram close enough. I am confused!! Where is the mistake? Note that, this is the main point of the question and IF CORRECT, the method needs just one "truncated-Gaussian" sample PLUS With the availability of existing fast algorithms, it leads to a huge savings (avoids divisions and multiplications, in addition to avoiding the need of relatively more complex truncated-ChiSquare) | |
| Jun 22, 2015 at 14:04 | history | edited | whuber♦ | CC BY-SA 3.0 |
added 107 characters in body
|
| Jun 22, 2015 at 14:02 | comment | added | whuber♦ | @Loves Yes I did--thank you for catching that. The code confirms you, too. I'll make the change. | |
| Jun 22, 2015 at 5:45 | comment | added | Loves Probability | I think you meant $F((a/\sigma)^2)$ instead of $F^{-1}((a/\sigma)^2)$ when you explained step-2. Is that right? | |
| Jun 22, 2015 at 5:27 | comment | added | Loves Probability | Thats a wonderful answer! But, can you also kindly throw some light on why the proposal-in-question fails? (Xi'an answer is not satisfactory enough, I see some problem with his argument e.g. when he integrates) | |
| Jun 21, 2015 at 16:03 | history | edited | whuber♦ | CC BY-SA 3.0 |
added 4 characters in body
|
| Jun 21, 2015 at 15:57 | history | answered | whuber♦ | CC BY-SA 3.0 |