kmte-package: An R Package for Treatment Effects with Censored Outcomes.
In pedrohcgs/kmte: An R Package for Treatment Effects with Censored Outcomes
Description
The kmte R package includes a variety of policy evaluations tools when the outcome of interest, typically a duration, is subjected to right
censoring. The content includes estimators and tests related to average, quantile and distributional treatment effects under different
identifying assumptions including unconfoundedness, local treatment effects, and nonlinear difrences-in-differences.
Details
In short, kmte implements all estimators proposed in Sant'Anna (2016a) "Program Evaluation with Right-Censored Data", and all tests proposed
in Sant'Anna (2016b), "Nonparametric Tests for Treatment Effect Heterogeneity with Duration Outcomes". Both articles are available at
Pedro H.C. Sant'Anna webpage, http://sites.google.com/site/pedrohcsantanna/ .
When the treatment is exogenous, i.e. under the unconfoundedness assumption,
one can use the following functions:
kmate - compute the Average Treatment Effect for possibly randomly censored data.
kmqte - compute the Quantile Treatment Effect for possibly randomly censored data.
kmdte - compute the Distributional Treatment Effect for possibly randomly censored data.
Alternatively, when the treatment is endogenous and we have a binary instrument, i.e. under the local treatment effect setup,
one can use the following functions:
kmlate - compute the Local Average Treatment Effect for possibly randomly censored data.
kmlqte - compute the Local Quantile Treatment Effect for possibly randomly censored data.
kmldte - compute the Local Distributional Treatment Effect for possibly randomly censored data.
In addition, the kmte package also implements the following nonparametric tests for treatment effect heterogeneity:
Under Unconfoundedness:
zcate - compute different tests for the null hypothesis of Zero Conditional Average Treatment Effetcs.
zcdte - compute different tests for the null hypothesis of Zero Conditional Distributional Treatment Effetcs.
hcate - compute different tests for the null hypothesis of Homogeneous Conditional Average Treatment Effetcs.
Under the Local Treatment Setup:
zclate - compute different tests for the null hypothesis of Zero Conditional Local Average Treatment Effetcs.
zcldte - compute different tests for the null hypothesis of Zero Conditional Local Distributional Treatment Effetcs.
hclate - compute different tests for the null hypothesis of Homogeneous Conditional Local Average Treatment Effetcs.
The module was written by Pedro H.C. Sant'Anna (Vanderbilt University).
A help file with examples will be made available in the near future.
pedrohcgs/kmte documentation built on May 24, 2019, 11:46 p.m.
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
Description
The kmte R package includes a variety of policy evaluations tools when the outcome of interest, typically a duration, is subjected to right censoring. The content includes estimators and tests related to average, quantile and distributional treatment effects under different identifying assumptions including unconfoundedness, local treatment effects, and nonlinear difrences-in-differences.
Details
In short, kmte implements all estimators proposed in Sant'Anna (2016a) "Program Evaluation with Right-Censored Data", and all tests proposed in Sant'Anna (2016b), "Nonparametric Tests for Treatment Effect Heterogeneity with Duration Outcomes". Both articles are available at Pedro H.C. Sant'Anna webpage, http://sites.google.com/site/pedrohcsantanna/ .
When the treatment is exogenous, i.e. under the unconfoundedness assumption, one can use the following functions:
kmate - compute the Average Treatment Effect for possibly randomly censored data.
kmqte - compute the Quantile Treatment Effect for possibly randomly censored data.
kmdte - compute the Distributional Treatment Effect for possibly randomly censored data.
Alternatively, when the treatment is endogenous and we have a binary instrument, i.e. under the local treatment effect setup, one can use the following functions:
kmlate - compute the Local Average Treatment Effect for possibly randomly censored data.
kmlqte - compute the Local Quantile Treatment Effect for possibly randomly censored data.
kmldte - compute the Local Distributional Treatment Effect for possibly randomly censored data.
In addition, the kmte package also implements the following nonparametric tests for treatment effect heterogeneity:
Under Unconfoundedness:
zcate - compute different tests for the null hypothesis of Zero Conditional Average Treatment Effetcs.
zcdte - compute different tests for the null hypothesis of Zero Conditional Distributional Treatment Effetcs.
hcate - compute different tests for the null hypothesis of Homogeneous Conditional Average Treatment Effetcs.
Under the Local Treatment Setup:
zclate - compute different tests for the null hypothesis of Zero Conditional Local Average Treatment Effetcs.
zcldte - compute different tests for the null hypothesis of Zero Conditional Local Distributional Treatment Effetcs.
hclate - compute different tests for the null hypothesis of Homogeneous Conditional Local Average Treatment Effetcs.
The module was written by Pedro H.C. Sant'Anna (Vanderbilt University).
A help file with examples will be made available in the near future.
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
Embedding an R snippet on your website
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.