search

donaldRwilliams / BGGM

Bayesian Gaussian Graphical Models
https://donaldrwilliams.github.io/BGGM/
GNU General Public License v2.0
54 stars 14 forks source link

Changing credibility level in estimate function #72

Closed tsbaguley closed 3 years ago

tsbaguley commented 3 years ago

For some reason I can't change the credibility level from 0.95. (Working from the CRAN version 2.03).

e.g.,

fit <- estimate(Y, type = "continuous", cred=0.99)

... or at least the lower and upper bounds from summary(fit) don't change. I have probably made a stupid error, but I've run out of brain cells to resolve this today.

donaldRwilliams commented 3 years ago

Hi. That would all be done after fitting. The reason is that then you do not have to re fit model in the event you wanted different cred.

see here

library(BGGM)

Y <- ptsd

fit <- estimate(Y)

summary(fit, cred = 0.90)

select(fit, cred = 0.90)

summary(fit, cred = 0.99)

select(fit, cred = 0.99)

# need to customize with ggplot to look nice
plot(summary(fit, cred = 0.99))
tsbaguley commented 3 years ago

Thank you so much - I knew it would be something basic. I'm doing some exploratory work and the 90% credibility plot makes more sense in this context. I love the package.

donaldRwilliams commented 3 years ago

No problem. And thanks !