Questions tagged [objective-bayes]
The objective-bayes tag has no usage guidance.
7
questions
0
votes
1
answer
56
views
What is the right Haar prior for the Weibull distribution?
From Wikipedia, the Weibull distribution is defined with the exceedance distribution function (aka survival function) $\exp[-(x/\lambda)^k]$.
If I transform the random variable $x$ using $x'=ax^b$ ...
- 109
2
votes
0
answers
94
views
Improper Prior in Logit and Probit Models: Proper Posterior Conditions
Let
$y_i \vert p_i \sim \mathrm{Bernoulli}(p_i)$,
$p_i = F_h(X_i^\prime \beta) \ \ , \ \ h = 1,2 \ ,\ \ X , \beta \in \mathbb R^p$,
where $F_1(x) = (2\pi)^{-1/2}\int_{-\infty}^x \exp(-t^2/2) \ dt \ $ ...
- 31
1
vote
1
answer
90
views
Is there any strong argument about objective/non-informative improper prior?
Decades ago improper objective priors - e.g. $\pi(\sigma) \propto \sigma^{-1}, \sigma > 0,$ for a scale parameter - were considered problematic because some authors thought they were leading to the ...
- 51
2
votes
0
answers
196
views
List of proper Jeffreys priors?
I know that Jeffreys priors are often improper. In fact, the only proper Jeffreys prior that I know is for the success probability in Bernoulli model (the prior arcsine).
I am curious to know if there ...
- 51
1
vote
1
answer
69
views
Example of a uniform prior not being objective
The key feature of a truly objective prior is that it is invariant under change of variables. I understand this concept, however, I'm having a hard time finding a simple 1D or 2D example of when you ...
- 151
5
votes
1
answer
460
views
Significance of parameterisation invariance of Jeffreys prior
I often hear it said that the Jeffreys prior is well-motivated because it is invariant under reparametrization. The proof of this is quite straight-forward (I know the proof on e.g., wiki). I'm a bit ...
- 1,430
2
votes
0
answers
25
views
Using some objective priors (for unbounded space) in a Metropolis-Hastings MCMC
I'm doing some simulations using a M-H MCMC, and I was thinking of using some objective priors for some parameters. These parameters must be in $\mathbb{R}^+$. I was thinking of using $\pi(\theta)\...
- 5,420