Returns a data frame with the columns 'mean', 'lower', and 'upper' reflecting the mean and lower and upper bounds of a confidence interval (quantiles) for every column in a data frame of draws
ci(df, level = 0.95)
A data frame of draws with all numeric columns.
The sensitivity of the computed confidence interval (CI).
Defaults to level = 0.95
, reflecting a 95% CI.
library(logitr)
# Estimate a preference space model
mnl_pref <- logitr(
data = yogurt,
outcome = "choice",
obsID = "obsID",
pars = c("price", "feat", "brand")
)
#> Running model...
#> Done!
# Obtain 10,000 draws of parameters from model
coefs <- coef(mnl_pref)
covariance <- vcov(mnl_pref)
coef_draws <- as.data.frame(MASS::mvrnorm(10^4, coefs, covariance))
# Compute a confidence interval
ci(coef_draws, level = 0.95)
#> mean lower upper
#> price -0.3664219 -0.4146429 -0.3181950
#> feat 0.4904642 0.2513380 0.7239711
#> brandhiland -3.7148090 -3.9958394 -3.4295248
#> brandweight -0.6415058 -0.7477549 -0.5338245
#> brandyoplait 0.7341273 0.5760748 0.8942999