5) Likelihood-based confidence interval and likelihood ratio Flashcards
1
Q
What is the Wilks log likelihood ratio statistic
A
2
Q
What are the advantages of using a likelihood-based CI
A
- Not restricted to be symmetric
- Enables to construct multivariate CIs for parameter vector easily even in non-normal cases
- Contains normal CI as special case
3
Q
What is the quadratic approximation of the Wilks statistic
A
4
Q
Under 𝜽0 how is the Wilks statistic distributed
A
5
Q
What are the critical values of the likelihood CI
A
6
Q
What is the likelihood ratio
A
7
Q
What is the relationship between the Wilk statistic and the likelihood ratio
A
𝑊(𝜽0) = −2 log Λ(𝜽0)
8
Q
How can the Wilks statistic be related to the KL divergence for specific models
A
