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

Suppose you want to estimate the parameters $\alpha$ and $\beta$ of a $\text{gamma}(\alpha, \beta)$ distribution where we know that $\alpha = \beta$. Would you treat this as a distribution with one or two unknown parameters? It seems that you can treat it as a distribution with 1 unknown parameter.

share|cite|improve this question
Are you saying that you know the mean of your gamma distribution is $1$? If so then yes, you can treat the shape and scale parameters as a single unknown, subject to that constraint. – Henry Apr 7 '12 at 17:36
@Henry: So if you have a $N(a, a^2)$ distribution with $a$ unknown, then if you find an estimator for $a$ you have found an estimator for $a^2$? – jameie ross Apr 7 '12 at 17:45
yes, and again in your $N(a,a^2)$ example it is subject to a constraint. – Henry Apr 7 '12 at 17:50
@Henry: I see. So you can find an estimator for the scale parameter (or shape parameter) and say that you have also found an estimator for the shape shape parameter (scale parameter)? – jameie ross Apr 7 '12 at 18:02
@Henry: In other words, you could say that the shape parameter is known and the scale parameter is unknown? – jameie ross Apr 7 '12 at 18:09

Your Answer


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

Browse other questions tagged or ask your own question.