How to do the sensitive analysis for the prior?

Ask Question

Asked 1 year, 5 months ago

Modified 1 year, 5 months ago

Viewed 18 times

I understand bayesian people always do the sensitive analysis for the study. However, I am confused how we set the sensitive analysis.

My question is how we set the parameter's for the sensitive analysis?

Is there any applied Bayesian hierarchical paper we can see for the sensitive analysis?

For example: we have a prior for the m~ dnorm(0,1)

the possible sensitive analysis

set m~ dnorm(0,100)

set m~ dnorm(100,1)

set m~ dnorm(100000,100000)

set m~ dgamma(0.5,1)

which sensitive analysis make more sense?

Thanks

asked Dec 10, 2020 at 5:35

hard worker

112 bronze badges

$\begingroup$ This paper "The Importance of Prior Sensitivity Analysis in Bayesian Statistics: Demonstrations Using an Interactive Shiny App" (frontiersin.org/articles/10.3389/fpsyg.2020.608045/full) with an Shiny app might be helpful for you. $\endgroup$
– TrungDung
Dec 10, 2020 at 21:54
$\begingroup$ I'm a big fan of prior predictive checks. Andrew Gelman and his collaborators write about these a lot, e.g., stat.columbia.edu/~gelman/bayescomputation/bdachapter6.pdf $\endgroup$
– statian
Dec 11, 2020 at 23:00

Add a comment |

0 Your Answer

Name

Required, but never shown

Post as a guest

Name

Required, but never shown

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy