Closed matthewravery closed 6 years ago
ciTools should now support binomial regression. This includes:
1) Functionality for PIs, probs, and quantiles for binomial regressions fit with glm 2) A TON of error messages (probably too many, TBH) 3) Fitted values that reflect E(Y|X) rather than pHat when estimating PIs, probs, and quantiles
Binomial (vice Bernoulli) regression is supported by GLM and can be specified by using the "weights" option to give the number of trials per observation and the response variable to indicate the proportion of "success"s. Prediction intervals, quantile estimates, and probability estimates are sensible for such cases and could be estimated via simulation.