These functions can be used to generated estimated values and associated confidence/prediction intervals for trending_model_fit objects.
# S3 method for trending_model_fit
predict(object, new_data, alpha = 0.05, add_pi = TRUE, uncertain = TRUE, ...)# S3 method for trending_model_fit_list
predict(object, new_data, alpha = 0.05, add_pi = TRUE, uncertain = TRUE, ...)
A trending_model_fit
or trending_model_fit_list
object.
A data.frame
containing data for which predictions are to
be derived.
The alpha threshold to be used for prediction intervals, defaulting to 0.05, i.e. 95% prediction intervals are derived.
Add a prediction interval to the output. Default TRUE.
Only used for glm models. Default TRUE. If FALSE uncertainty in the fitted paramaters is ignored when generating the prediction intervals.
Not currently used.
x = rnorm(100, mean = 0) y = rpois(n = 100, lambda = exp(1.5 + 0.5*x)) dat <- data.frame(x = x, y = y)
poisson_model <- glm_model(y ~ x , family = "poisson") negbin_model <- glm_nb_model(y ~ x)
fitted_poisson <- fit(poisson_model, dat) fitted_list <- fit(list(poisson_model, negbin_model), dat)
predict(fitted_poisson) predict(fitted_list)