Finding the mle for the gamma distribution

Click For Summary
SUMMARY

The discussion focuses on finding the maximum likelihood estimator (MLE) for the gamma distribution, specifically addressing the parameter \(\theta\) represented as alpha. The likelihood function is defined as \(L(\theta) = \frac{1}{\Gamma(\theta)\beta^{\theta}} x^{\theta-1} e^{-x/\beta}\). Participants discuss the natural logarithm of the likelihood function and the challenge of differentiating the factorial term \((1-\theta)!\). The solution involves using the gamma function and its derivatives, particularly the polygamma function, to resolve the differentiation issue.

PREREQUISITES
  • Understanding of maximum likelihood estimation (MLE)
  • Familiarity with gamma distribution and its properties
  • Knowledge of differentiation techniques in calculus
  • Basic understanding of the polygamma function
NEXT STEPS
  • Study the properties of the gamma function and its derivatives
  • Learn about the polygamma function and its applications in statistics
  • Explore maximum likelihood estimation for different probability distributions
  • Practice differentiation of complex functions involving factorials and gamma functions
USEFUL FOR

Statisticians, data scientists, and mathematicians interested in statistical estimation methods and the properties of the gamma distribution.

Artusartos
Messages
236
Reaction score
0
So if the parameter \theta is alpha...

L(\theta) = \frac{1}{\Gamma(\theta)\beta^{\theta}} x^{\theta-1} e^{-x/\beta}

Now I take the natural log of that...


ln(L(\theta)) = ln(\frac{1}{(1-\theta)!}) + ln(\frac{1}{\beta^{\theta}}) + ln(x^{\theta-1}) + ln(e^{-x/\beta})

Now I want to take the derivative of this...but I'm stuck because I don't know what the derivative of \frac{1}{(1-\theta)!} is...how can I find the derivative of a factorial? :confused:
 
Physics news on Phys.org
Why did you replace the gamma function with the factorial in the first place? Differentiate the gamma function, problem solved.
 

Similar threads

Replies
2
Views
1K
  • · Replies 3 ·
Replies
3
Views
2K
Replies
3
Views
2K
Replies
7
Views
3K
  • · Replies 1 ·
Replies
1
Views
2K
  • · Replies 10 ·
Replies
10
Views
2K
  • · Replies 3 ·
Replies
3
Views
2K
  • · Replies 2 ·
Replies
2
Views
1K
  • · Replies 3 ·
Replies
3
Views
2K
  • · Replies 4 ·
Replies
4
Views
2K