toy_data

This toy data has 100 observations/units with 20 categorical covariates.

datasets

The 'FLAME' (Fast Large-scale Almost Matching Exactly) package implements the
matching algorithm in Roy, Rudin, Volfovsky, and Wang (2017) <arXiv:1707.06315>. 'FLAME'
performs matching of treatment and control units in the potential outcomes framework
for large categorical datasets. 'FLAME' creates matches that include as many covariates
as possible, and sequentially drops covariates that are less useful based on a match
quality measure. Match quality combines two important elements <e2><80><93> it considers predictive
power from machine learning on a hold out training set, and a balancing factor to ensure
that it does not remove a covariate that would ruin overlap between treatment and
control groups. Currently the 'FLAME' package applies to categorical data, and
provides two approaches for implementation - bit vectors and database management systems
(e.g., 'PostgreSQL', 'SQLite'). For data that has been adequately processed and fits in memory,
bit vectors should be applied. For extremely large data that does not fit in memory, database
systems should be applied.

Chia-Rui (Jerry) Chang

FLAME

A Fast Large-Scale Almost Matching Exactly Approach to Causal
Inference

Cynthia Rudin

Alexander Volfovsky

Sudeepa Roy

Tianyu Wang

toy_data function

A data frame with 2190410 rows and 86 covariates:<dl class="dl-horizontal">
 <dt>X1</dt><dd>9 levels</dd>
 <dt>X2</dt><dd>9 levels</dd>
 <dt>X3</dt><dd>9 levels</dd>
 <dt>X4</dt><dd>9 levels</dd>
 <dt>X5</dt><dd>8 levels</dd>
 <dt>X6</dt><dd>8 levels</dd>
 <dt>X7</dt><dd>8 levels</dd>
 <dt>X8</dt><dd>7 levels</dd>
 <dt>X9</dt><dd>5 levels</dd>
 <dt>X10</dt><dd>5 levels</dd>
 <dt>X11</dt><dd>4 levels</dd>
 <dt>X12</dt><dd>3 levels</dd>
 <dt>X13</dt><dd>3 levels</dd>
 <dt>X14</dt><dd>2 levels</dd>
 <dt>X15</dt><dd>2 levels</dd>
 <dt>X16</dt><dd>2 levels</dd>
 <dt>X17</dt><dd>2 levels</dd>
 <dt>X18</dt><dd>2 levels</dd>
 <dt>X19</dt><dd>2 levels</dd>
 <dt>X20</dt><dd>2 levels</dd>
 <dt>outcome</dt><dd>Outcome Variable</dd>
 <dt>treated</dt><dd>Treated = 1, Control = 0</dd>
</dl>

Format

Toy Data — toy_data

A data frame with 2190410 rows and 86 covariates:<dl class='dl-horizontal'>
 <dt>X1</dt><dd>9 levels</dd>
 <dt>X2</dt><dd>9 levels</dd>
 <dt>X3</dt><dd>9 levels</dd>
 <dt>X4</dt><dd>9 levels</dd>
 <dt>X5</dt><dd>8 levels</dd>
 <dt>X6</dt><dd>8 levels</dd>
 <dt>X7</dt><dd>8 levels</dd>
 <dt>X8</dt><dd>7 levels</dd>
 <dt>X9</dt><dd>5 levels</dd>
 <dt>X10</dt><dd>5 levels</dd>
 <dt>X11</dt><dd>4 levels</dd>
 <dt>X12</dt><dd>3 levels</dd>
 <dt>X13</dt><dd>3 levels</dd>
 <dt>X14</dt><dd>2 levels</dd>
 <dt>X15</dt><dd>2 levels</dd>
 <dt>X16</dt><dd>2 levels</dd>
 <dt>X17</dt><dd>2 levels</dd>
 <dt>X18</dt><dd>2 levels</dd>
 <dt>X19</dt><dd>2 levels</dd>
 <dt>X20</dt><dd>2 levels</dd>
 <dt>outcome</dt><dd>Outcome Variable</dd>
 <dt>treated</dt><dd>Treated = 1, Control = 0</dd>
</dl>

toy_data: Toy Data

Description

Usage

Arguments

Format