I am working through the 2023 version of the Statistical Rethinking course, and I have gotten stuck embarrassingly early in my attempt to use brms. In lecture “bonus” material, McElreath asks how we could model the proportion of water on the globe but with a twist. The twist is that for x proportio…

If you know the misclassification rates, then I think the most general way to approach a problem like this is marginalize over the possible true data values according to the classification probabilities. We could achieve this in brms, if desired, via a custom family that takes the known misclassifi…

In the very most general case, where every pixel comes with its own misclassification probability, we would set up the linear predictor and logistic inverse link, but in place of binary 1/0 data the data would be the probability that the response is 1, and the likelihood would be target += log_sum_…

Hi all, my previous post here is incorrect. We need to marginalize over two possibilities: that the true state is zero and that the true state is one. However, to achieve this we need likelihoods not based on y[i] the a priori probability that the true state is one, but rather on z[i], the likelih…

Does the Rethinking package let you generate the Stan code? If so, can you post it?

Misclassification or measurement error for binomial model with brms (Statistical Rethinking 2023)

Interfaces brms

Solomon February 5, 2023, 9:00pm 3

If anyone has the code for this, I’d love to see it.

Binary data with known missclasification rate

Topic		Replies	Views
Binary data with known missclasification rate Modeling rstan , specification	9	986	July 9, 2023
Using BRMS when the dichotomous outcome is measured with error brms	6	853	October 9, 2019
Predictor including error but allowing to be estimate by a supplementary dataset brms	3	428	April 18, 2023
Parameterization of measurement error in brms brms	4	902	September 7, 2018
Regression with measurement error in brms brms specification	4	1975	October 6, 2021

Misclassification or measurement error for binomial model with brms (Statistical Rethinking 2023)

Related topics