Obtain the prior distribution for a function's parameter

Specific Domains Statistics
1

Hi, all. I met a problem getting the prior distribution for parameters in a function f(x; b, s, q). I wish to obtain a dict ParaDict = Dict(:b => b, :s => s, :q => q) in form of

b ~ truncated(Normal(1., 1), 0, 5)
s  ~ truncated(Normal(0., 1), 0, 0.1)
q  ~ truncated(Normal(0.5, 1.0), 0.1, 1)

    
ParaDict = Dict(:b => b, :s => s, :q => q)
2

Priors (in Bayesian estimation) are chosen by the statistician. Your question does not make sense in this form.

Is this a homework problem?

3

No, the prior is fixed as truncated(Normal(m, sigma), lower, upper). I just don’t know how to make

b ~ truncated(Normal(1., 1), 0, 5); 
Dict(:b =>b)

from b in f(x;b)

4

I feel like there’s something missing context in your question. In general, a function f may have nothing to do with priors at all or express it in some arbitrarily convoluted way that cannot be easily extracted.

I’m assuming the context for this is that the function is one defined through the use of the @model macro from Turing.jl? If not, you will need to give more information, ideally with a full example of the function you would like to extract that information from.