Suppose I have a sequence of iid random variables $X_1, \ldots, X_n$ following the pdf:

$$ f_\theta (x) = \theta x^{\theta-1} $$

for $\theta >0$ and $0 <x<1$.

I would like to find a sufficient statistic $T(X)$, such that the family $f_\theta (x)$ has a monotone likelihood ratio (MLR) in $T(X)$.

I do this by having:

$$ \frac{f(x|\theta_1)}{f(x|\theta_2)} = \frac{\prod_{i=1}^{n}\theta_1x_i^{\theta_1-1}}{\prod_{i=1}^{n}\theta_2x_i^{\theta_2-1}} = \left(\frac{\theta_1}{\theta_2}\right)^n \prod_{i=1}^n\left(x_i\right)^{\theta_1-\theta_2} = \left(\frac{\theta_1}{\theta_2}\right)^n \left(\prod_{i=1}^nx_i\right)^{\theta_1-\theta_2} $$

At this point, is the sufficient statistic corresponding to the MLR, $T(X) = \prod_{i=1}^nx_i$?

Or would it be:

$$ \frac{f(x|\theta_1)}{f(x|\theta_2)} = \left(\frac{\theta_1}{\theta_2}\right)^n \left(\prod_{i=1}^nx_i\right)^{\theta_1-\theta_2} = \left(\frac{\theta_1}{\theta_2}\right)^n \left(e^{\sum_{i=1}^n \log(x_i)}\right)^{\theta_1-\theta_2} $$

and hence the sufficient statistic is $\sum_{i=1}^n \log(x_i)$? I understand that sufficient statistics are not unique, but which one of the above is the right answer?

Is it $T(X) = \prod_{i=1}^nx_i$ or $T(X) =\sum_{i=1}^n \log(x_i)$?


Both works.

$$T_1(X) = \prod_{i=1}^nx_i$$ $$T_2(X) =\sum_{i=1}^n \log(x_i)$$

Notice that $$T_2(x)=\log(T_1(X))$$ and $$T_1(X)=\exp(T_2(X)),$$ injective function maps a sufficient statistics to another sufficient statistics.

  • $\begingroup$ Will the distributions be different for each? $\endgroup$ – user321627 Dec 27 '16 at 16:41
  • 1
    $\begingroup$ Given a set $X$ of independent identically distributed data conditioned on an unknown parameter $\theta$ , a sufficient statistic is a function $T(X)$ whose value contains all the information needed to compute any estimate of the parameter. It is a way to summarize the data. Both of them summarizes the same distribution. $\endgroup$ – Siong Thye Goh Dec 27 '16 at 19:11
  • 1
    $\begingroup$ rather than "the" sufficient statistics, i think it should be "a" sufficient statistics. The distribution of $T_1(X)$ and $T_2(X)$ are different but they can be transformed from one to the other. $\endgroup$ – Siong Thye Goh Dec 27 '16 at 19:17

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.