Exponential family: f(x|theta)=c(x)d(theta)exp[a(theta)b(x)], T = sum b(x_i) Show that T is a sufficient statistic

June Mejia

June Mejia

Open question

2022-08-17

Exponential family:
f ( x | θ ) = c ( x ) d ( θ ) exp [ a ( θ ) b ( x ) ]
T = b ( x i )
Show that T is a sufficient statistic

Answer & Explanation

Sage Braun

Sage Braun

Beginner2022-08-18Added 11 answers

The point of sufficiency is not quite what you said. Let's say you have a density f ( x | θ ) and that it factors like this:
f ( x | θ ) = h ( x ) g ( θ , T ( x ) )
In other words, the density factors into a part which involves only data (the function h), and into a part which depends on both the parameter θ and a function of the data T ( x ) (the function g). In this case the function T is said to be a sufficient statistic for θ.
The intuition behind this is that since h ( x ) can be factored out from g, then it has no "interaction" with θ so any information contained in h ( x ) will not affect your ability to estimate θ. The only part of the data that matters is T ( x ), since it interacts with θ through the function g.
In the exponential case, the factorization is h ( x ) = c ( x ) and g ( θ , T ( x ) ) = d ( θ ) exp ( a ( θ ) , b ( x ) ). Thus g depends on x solely through the function b ( x ).

Do you have a similar question?

Recalculate according to your conditions!

New Questions in College Statistics

Ask your question.
Get an expert answer.

Let our experts help you. Answer in as fast as 15 minutes.

Didn't find what you were looking for?