Need help to estimate adequately the parameters of a logistic model

Interfaces brms
1

I analyzed a data matrix using the Rasch model but I have the next problem: I need to inverse the sign of every estimated item difficulty to have a credible value. For example, if brm function return me a value of .9 for a specific item, I have to inverse the sign so the value of -.9 is the good one. Anybody knows how I can fix this with the next code?

Thanks!

formula15 <- bf(Xb15 ~ 1 + (1 | It15) + (1 | P15))
prior15 <- prior(“normal(0, 3)”, class = “sd”, group = “It15”) + prior(“normal(0, 3)”, class = “sd”, group = “P15”)
fit15 <- brm(formula = formula15,
data = X15,
family = brmsfamily(“bernoulli”,“logit”),
prior = prior15)

2

I guess the estimates are for intercepts instead of item difficulties. In IRT intercepts and item difficulties have exactly the opposite values, so you’re good.

3

Thank you so much for your answer :-) In this case, do you think I can also simply inverse the values of the 95% credible intervals from the output of the brm function?

4

yes. as long as your model itself is correct, intercepts are exactly the negative item difficulties.