haldensify
development notes...
args to haldensify()
to allow arbitrary arguments to be
passed directly to fit_hal()
.use_future
argument to haldensify()
, instead reducing to
calling future_mapply()
, with sequential evaluation via plan(sequential)
.rsample
.plot()
method to more easily visualize how empirical risk changes
across the sequence of explored regularization parameter values.ipw_shift()
function for constructing IPW estimators of the mean
counterfactual outcome of a stochastic shift intervention via haldensify
.haldensify()
to allow normalization of the density
estimates to improve estimation stability. Note that this normalized density
is actually g(A|W)/g(A), instead of the currently estimated g(A|W).Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.