jack_est: Estimate of Effect Measure and CI With Jacknife (LOO)

In FrankLef/fciR: Data and functions used with Fundamentals of Causal Inference by Babette Brumback

Estimate of Effect Measure and CI With Jacknife (LOO)

Description

Estimate of effect measure and CI With jacknife (LOO).

Usage

jack_est(data, func, alpha = 0.05, transf = c("identity", "exp", "expit"), ...)

jackiv.r(data, func, alpha = 0.05, transf = c("identity", "exp", "expit"), ...)

Arguments

data	Dataframe of raw data.
func	Function to estimate the effect measure.
alpha	Alpha used by percentile to give interval in c(alpha, 1- alpha).
transf	Type of conversion. Must be one of c("identity", "exp", "expit"), default is identity.
...	Other named arguments for func.

Details

Compute the confidence interval of effect measures using the jacknife method. It uses the loo_cv function from the rsample package. The jacknife funciton from the resample is not maintained anymore and the author of resample recommend using the rsample package. The output is transformed with inverse function when required. See section 9.3 of the book for more details.

Value

Dataframe of estimates with confidence interval.

See Also

jack_run jack_ci effect_transf

FrankLef/fciR documentation built on Nov. 12, 2023, 6:09 a.m.