sample_split

Splits the sample into training and honest subsamples.

Nonparametric data-driven approach to discovering heterogeneous subgroups in a selection-on-observables framework.
'aggTrees' allows researchers to assess whether there exists relevant heterogeneity in treatment effects by generating a sequence of optimal groupings,
one for each level of granularity. For each grouping, we obtain point estimation and inference about the group average treatment effects.
Please reference the use as Di Francesco (2022) <doi:10.2139/ssrn.4304256>.

Riccardo Di Francesco

aggTrees

Aggregation Trees

sample_split function

<dl><dt>n</dt>
<dd>Size of the sample to be split.</dd>
<dt>training_frac</dt>
<dd>Fraction of units for the training sample.</dd></dl>

Arguments

Author

Sample Splitting — sample_split

<dl>

<dt>n</dt>
<dd>Size of the sample to be split.</dd>


<dt>training_frac</dt>
<dd>Fraction of units for the training sample.</dd>

</dl>

sample_split: Sample Splitting

Description

Usage

Value

Arguments

Author