Timeline for How I determine the probability that an unknown probability value is greater than others in a set?
Current License: CC BY-SA 2.5
8 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Feb 11, 2011 at 2:44 | comment | added | Shai Covo | Note that a ${\rm Beta}(\alpha,\beta)$ random variable with $\alpha$ quite low and $\beta$ very large has small mean $\approx \frac{\alpha }{\beta }$ and very small variance $\approx \frac{\alpha }{\beta^2 }$. This may guide you a little bit and give you some ideas. | |
| Feb 10, 2011 at 19:03 | comment | added | sanity | The parameters will be integers, one of them might be quite low (1-5), the other might be in the thousands or even tens of thousands. | |
| Feb 10, 2011 at 1:36 | comment | added | Shai Covo | In the context of my last comment, it is worth noting that a ${\rm Beta}(\alpha,\beta)$ random variable has mean $\frac{\alpha }{{\alpha + \beta }}$ and variance $\frac{{\alpha \beta }}{{(\alpha + \beta )^2 (\alpha + \beta + 1)}}$. | |
| Feb 9, 2011 at 22:32 | comment | added | Shai Covo | If the parameters are very large, as you indicated above, then you should include as much details as you can. | |
| Feb 9, 2011 at 21:19 | comment | added | Shai Covo | Indeed, this wouldn't work in that situation. Are the parameters $\alpha_i$ and $\beta_i$ integers? How large $n$ typically is? | |
| Feb 9, 2011 at 21:11 | comment | added | sanity | Hmmm, unfortunately typical values of alpha and beta in my application might be 1,000 and 1,000,000 respectively. I'm guessing this wouldn't work in that situation? | |
| Feb 9, 2011 at 18:53 | history | edited | Shai Covo | CC BY-SA 2.5 |
added 453 characters in body; added 10 characters in body
|
| Feb 9, 2011 at 15:11 | history | answered | Shai Covo | CC BY-SA 2.5 |