Package {qte}

qte: A package for computing quantile treatment effects

Description

Provides several methods for computing the Quantile Treatment Effect (QTE) and Quantile Treatment Effect on the Treated (QTT). The main cases covered are (i) treatment is randomly assigned, (ii) treatment is as good as randomly assigned after conditioning on covariates (selection on observables) using the methods of Firpo (2007) doi:10.1111/j.1468-0262.2007.00738.x, and (iii) identification is based on a Difference in Differences assumption, with support for several varieties including Athey and Imbens (2006) doi:10.1111/j.1468-0262.2006.00668.x, Callaway and Li (2019) doi:10.3982/QE935, and Callaway, Li, and Oka (2018) doi:10.1016/j.jeconom.2018.06.008. Version 2.0 adds a unified staggered treatment adoption API (built on 'ptetools') for all DiD-based estimators, as well as a new lagged-outcome unconfoundedness estimator ('lou_qtt').

Author(s)

Maintainer: Brantly Callaway brantly.callaway@uga.edu

Authors:

• Brantly Callaway brantly.callaway@uga.edu

See Also

Useful links:

• https://bcallaway11.github.io/qte/

• https://github.com/bcallaway11/qte

• Report bugs at https://github.com/bcallaway11/qte/issues

CiC

Description

Deprecated. Use cic instead.

CiC is a legacy two-period wrapper for the Change in Changes estimator. It accepts a formula and explicit t/tmin1 time period arguments. The modern replacement cic uses a yname/gname/tname interface and supports staggered treatment adoption natively via ptetools.

Usage

CiC(
  formla,
  xformla = NULL,
  t,
  tmin1,
  tname,
  data,
  panel = FALSE,
  se = TRUE,
  idname = NULL,
  alp = 0.05,
  probs = seq(0.05, 0.95, 0.05),
  iters = 100,
  pl = FALSE,
  cores = 2,
  retEachIter = FALSE
)

Arguments

Value

QTE object.

See Also

cic

MDiD

Description

Deprecated. Use mdid instead.

MDiD is a legacy two-period wrapper for the Mean Difference-in-Differences estimator. The modern replacement mdid uses a yname/gname/tname interface and supports staggered treatment adoption natively.

Usage

MDiD(
  formla,
  xformla = NULL,
  t,
  tmin1,
  tname,
  data,
  panel = FALSE,
  se = TRUE,
  idname = NULL,
  alp = 0.05,
  probs = seq(0.05, 0.95, 0.05),
  iters = 100,
  retEachIter = FALSE,
  biters = NULL
)

Arguments

Value

QTE object.

See Also

mdid

QDiD

Description

Deprecated. Use qdid instead.

QDiD is a legacy two-period wrapper for the Quantile Difference-in-Differences estimator. It accepts a formula and explicit t/tmin1 time period arguments. The modern replacement qdid uses a yname/gname/tname interface and supports staggered treatment adoption natively.

Usage

QDiD(
  formla,
  xformla = NULL,
  t,
  tmin1,
  tname,
  data,
  panel = FALSE,
  se = TRUE,
  idname = NULL,
  alp = 0.05,
  probs = seq(0.05, 0.95, 0.05),
  iters = 100,
  retEachIter = FALSE,
  pl = FALSE,
  cores = NULL,
  biters = NULL,
  cl = NULL
)

Arguments

Value

QTE object.

See Also

qdid

QTE

Description

Main class of objects. A QTE object is returned by all of the methods that compute the QTE or QTET.

Usage

QTE(
  qte,
  ate = NULL,
  qte.se = NULL,
  qte.lower = NULL,
  qte.upper = NULL,
  ate.se = NULL,
  ate.lower = NULL,
  ate.upper = NULL,
  c = NULL,
  alp = 0.05,
  pscore.reg = NULL,
  probs,
  type = "On the Treated",
  F.treated.t = NULL,
  F.untreated.t = NULL,
  F.treated.t.cf = NULL,
  F.treated.tmin1 = NULL,
  F.treated.tmin2 = NULL,
  F.treated.change.tmin1 = NULL,
  F.untreated.change.t = NULL,
  F.untreated.change.tmin1 = NULL,
  F.untreated.tmin1 = NULL,
  F.untreated.tmin2 = NULL,
  condQ.treated.t = NULL,
  condQ.treated.t.cf = NULL,
  eachIterList = NULL,
  inffunct = NULL,
  inffuncu = NULL
)

Arguments

QTEparams

Description

QTEparams is an object that contains all the parameters passed to QTE methods

Usage

QTEparams(
  formla,
  xformla = NULL,
  t = NULL,
  tmin1 = NULL,
  tmin2 = NULL,
  tname = NULL,
  data,
  panel = FALSE,
  w = NULL,
  idname = NULL,
  probs,
  alp = NULL,
  method = NULL,
  plot = NULL,
  se = NULL,
  iters = NULL,
  retEachIter = NULL,
  bootstrapiter = NULL,
  seedvec = NULL,
  pl = NULL,
  cores = NULL,
  est_method = NULL,
  target = NULL
)

Arguments

Value

A named list with class "QTEparams" containing all supplied arguments. Used internally by legacy estimators (CiC, QDiD, MDiD, ddid2, panel.qtet, ci.qtet) to pass parameters to setupData and compute.* functions.

SE

Description

Class for Standard Error Objects

Usage

SE(
  qte.se = NULL,
  ate.se = NULL,
  qte.upper = NULL,
  qte.lower = NULL,
  ate.upper = NULL,
  ate.lower = NULL,
  c = NULL,
  probs = NULL
)

Arguments

autoplot.QTE

Description

Plot a QTE object as a quantile treatment effect curve with optional confidence bands.

Usage

## S3 method for class 'QTE'
autoplot(object, cband = TRUE, ylab = "QTE", ...)

Arguments

Value

a ggplot object.

bootiter

Description

bootiter that computes a single bootstrap iteration

Usage

bootiter(i, qteparams, func)

Arguments

Value

SE object

bootstrap

Description

bootstrap is a method that bootstraps standard errors for methods in the qte package

Usage

bootstrap(qteparams, qteest, func)

Arguments

Value

SE object

ci.qte

Description

Deprecated. Use unc_qte instead.

Usage

ci.qte(
  formla,
  xformla = NULL,
  x = NULL,
  data,
  w = NULL,
  probs = seq(0.05, 0.95, 0.05),
  se = TRUE,
  iters = 100,
  alp = 0.05,
  method = "logit",
  retEachIter = FALSE,
  printIter = FALSE,
  pl = FALSE,
  cores = 2,
  biters = NULL,
  cl = NULL
)

Arguments

Value

A QTE object; same structure as unc_qte.

ci.qtet

Description

Deprecated. Use unc_qte(target = "qtt") for a cross-sectional QTT under unconfoundedness, or lou_qtt for staggered treatment adoption with optional lagged-outcome conditioning.

ci.qtet estimates the Quantile Treatment Effect on the Treated (QTET) under a Conditional Independence Assumption (sometimes called Selection on Observables) following Firpo (2007). It uses propensity score re-weighting to estimate the counterfactual distribution. Standard errors are computed via the bootstrap.

Usage

ci.qtet(
  formla,
  xformla = NULL,
  w = NULL,
  data,
  probs = seq(0.05, 0.95, 0.05),
  se = TRUE,
  iters = 100,
  alp = 0.05,
  method = "logit",
  retEachIter = FALSE,
  indsample = TRUE,
  printIter = FALSE,
  pl = FALSE,
  cores = 2,
  biters = NULL,
  cl = NULL
)

Arguments

Value

A QTE object; same structure as unc_qte.

References

Firpo, Sergio. “Efficient Semiparametric Estimation of Quantile Treatment Effects.” Econometrica 75.1, pp. 259-276, 2007.

Examples

# See ?unc_qte for the modern replacement.
## Not run: 
data(lalonde)

## Estimate the QTET of participating in the job training program;
## This is the no covariate case.  Note: Because individuals that participate
## in the job training program are likely to be much different than
## individuals that do not (e.g. less experience and less education), this
## method is likely to perform poorly at estimating the true QTET
q1 <- ci.qtet(re78 ~ treat,
  x = NULL, data = lalonde.psid, se = FALSE,
  probs = seq(0.05, 0.95, 0.05)
)
summary(q1)

## This estimation controls for all the available background characteristics.
q2 <- ci.qtet(re78 ~ treat,
  xformla = ~ age + I(age^2) + education + black + hispanic + married + nodegree,
  data = lalonde.psid, se = FALSE, probs = seq(0.05, 0.95, 0.05)
)
summary(q2)

## End(Not run)

Change in Changes

Description

Computes Quantile Treatment effects on the Treated (QTT) and the Average Treatment Effect on the Treated (ATT) using the Change in Changes identification strategy of Athey and Imbens (2006). Handles two-period data and staggered treatment adoption uniformly: a two-period, two-group dataset is the degenerate single-(g,t) case. Supports both panel and repeated cross sections data.

Usage

cic(
  yname,
  gname,
  tname,
  idname = NULL,
  data,
  panel = TRUE,
  xformula = ~1,
  weightsname = NULL,
  control_group = "notyettreated",
  anticipation = 0,
  alp = 0.05,
  cband = TRUE,
  biters = 100,
  cl = 1,
  ret_quantile = NULL,
  gt_type = "att",
  probs = NULL
)

Arguments

Value

For gt_type = "att", a pte_results object from ptetools. For gt_type = "qtt", a pte_qtt object with overall, group-specific, and dynamic QTT curves and bootstrap SEs.

References

Athey, Susan and Guido Imbens. “Identification and Inference in Nonlinear Difference-in-Differences Models.” Econometrica 74(2), pp. 431-497, 2006.

Examples

data(mpdta, package = "did")

## ATT aggregated across all groups and periods
res_att <- cic(yname = "lemp", gname = "first.treat", tname = "year",
               idname = "countyreal", data = mpdta,
               gt_type = "att", biters = 20)
summary(res_att)

## Full QTT curve at selected quantiles
res_qtt <- cic(yname = "lemp", gname = "first.treat", tname = "year",
               idname = "countyreal", data = mpdta,
               gt_type = "qtt", probs = seq(0.1, 0.9, 0.1), biters = 20)
summary(res_qtt)

Change in Changes: group-time estimator

Description

Computes the Change in Changes (CiC) ATT and counterfactual outcome distribution for a single 2x2 (pre/post x treated/control) data subset. Serves directly as the attgt_fun argument to ptetools::pte. Panel vs. repeated cross sections is detected automatically from whether the same unit ids appear in both periods.

Usage

cic_gt(gt_data, xformula = ~1, ...)

Arguments

Value

A ptetools::attgt_noif object with the ATT estimate and, in extra_gt_returns, three objects: F1 (ECDF of observed treated outcomes in the post period), F0 (ECDF of counterfactual untreated outcomes for the treated group), and Fte (ECDF of individual treatment effects under rank invariance; NULL for repeated cross sections).

References

Athey, Susan and Guido Imbens. “Identification and Inference in Nonlinear Difference-in-Differences Models.” Econometrica 74(2), pp. 431-497, 2006.

compute.panel.qtet

Description

compute.panel.qtet uses third period of data, combined with Distributional Difference in Differences assumption (Fan and Yu, 2012) to point identify QTET.

Usage

compute.panel.qtet(qp)

Arguments

Value

QTE object

compute.unc_qte

Description

Computes the QTE or QTT under unconfoundedness. Dispatches to IPW, OR (outcome regression), or AIPW based on qp$est_method and qp$target. Called internally by unc_qte and during each bootstrap iteration.

Usage

compute.unc_qte(qp)

Arguments

Value

QTE object

computeSE

Description

Computes standard errors from bootstrap results. This function is called by several functions in the qte package

Usage

computeSE(bootIters, qteobj, alp = 0.05)

Arguments

Value

SEObj

Distributional Difference-in-Differences

Description

Computes Quantile Treatment effects on the Treated (QTT) and the Average Treatment Effect on the Treated (ATT) using the distributional DiD identification strategy of Callaway, Li, and Oka (2018). Handles two-period data and staggered treatment adoption uniformly via ptetools. Requires panel data.

Identification. Under distributional parallel trends and a copula restriction (the rank correlation of untreated potential outcomes between the treated and control groups in the pre-period is preserved), the counterfactual distribution F_{Y(0),\text{post}|D=1} is recovered by adding each control unit's actual change \Delta Y_{\text{ctrl},j} to the treated pre-period quantile at that control unit's rank. This point-identifies the QTT with only two time periods, in contrast to methods (e.g. panel_qtt) that require three periods.

Panel data required. Unlike cic, qdid, and mdid, this estimator cannot be applied to repeated cross sections because it requires observing the within-unit outcome change for each control unit.

Usage

ddid(
  yname,
  gname,
  tname,
  idname,
  data,
  xformula = ~1,
  weightsname = NULL,
  control_group = "notyettreated",
  anticipation = 0,
  alp = 0.05,
  cband = TRUE,
  biters = 100,
  cl = 1,
  gt_type = "att",
  probs = NULL
)

Arguments

Value

For gt_type = "att", a pte_results object from ptetools. For gt_type = "qtt", a pte_qtt object.

References

Callaway, Brantly, Tong Li, and Tatsushi Oka. “Quantile Treatment Effects in Difference in Differences Models under Dependence Restrictions and with Only Two Time Periods.” Journal of Econometrics 206(2), pp. 395-413, 2018.

Examples

data(mpdta, package = "did")

## ATT aggregated across all groups and periods
res_att <- ddid(yname = "lemp", gname = "first.treat", tname = "year",
                idname = "countyreal", data = mpdta,
                gt_type = "att", biters = 20)
summary(res_att)

## Full QTT curve at selected quantiles
res_qtt <- ddid(yname = "lemp", gname = "first.treat", tname = "year",
                idname = "countyreal", data = mpdta,
                gt_type = "qtt", probs = seq(0.1, 0.9, 0.1), biters = 20)
summary(res_qtt)

ddid2

Description

Deprecated. Use ddid instead.

ddid2 is a legacy two-period wrapper for the Distributional Difference-in-Differences estimator. The modern replacement ddid uses a yname/gname/tname interface and supports staggered treatment adoption natively.

Usage

ddid2(
  formla,
  xformla = NULL,
  t,
  tmin1,
  tname,
  data,
  panel = TRUE,
  dropalwaystreated = TRUE,
  idname = NULL,
  probs = seq(0.05, 0.95, 0.05),
  iters = 100,
  alp = 0.05,
  method = "logit",
  se = TRUE,
  retEachIter = FALSE,
  seedvec = NULL,
  pl = FALSE,
  cores = NULL,
  biters = NULL,
  cl = NULL
)

Arguments

Value

QTE object.

See Also

ddid

Distributional DiD: group-time estimator

Description

Computes the distributional DiD ATT and counterfactual outcome distribution for a single 2x2 (pre/post x treated/control) data subset. Serves directly as the attgt_fun argument to ptetools::pte.

Identification. Under distributional parallel trends and a copula restriction (Callaway, Li, and Oka 2018), the counterfactual outcome for each control unit j is

kcf_j = \Delta Y_{\text{ctrl},j} + Q_{1,\text{pre}}(u_j)

where \Delta Y_{\text{ctrl},j} = Y_{\text{post},j} - Y_{\text{pre},j} is the observed change for control unit j, u_j = F_{0,\text{pre}}(Y_{\text{pre},j}) is that unit's rank in the control pre-period distribution, and Q_{1,\text{pre}} is the quantile function of the treated pre-period distribution. The unconditional counterfactual distribution F_{Y(0),\text{post}|D=1} is then the (weighted) empirical CDF of \{kcf_j\}.

Unlike CiC, QDiD, and MDiD, the counterfactual is indexed over control units, not treated units. Consequently F0 and the ATT counterfactual term are weighted by w_pre_ctrl, and no individual treatment effect distribution (Fte) is returned.

Panel data required. The estimator needs the actual change \Delta Y_{\text{ctrl},j} for each control unit, which requires observing the same units in both periods.

Usage

ddid_gt(gt_data, xformula = ~1, ...)

Arguments

Value

A ptetools::attgt_noif object with the ATT estimate and, in extra_gt_returns, F0 (weighted ECDF of counterfactual outcomes indexed over control units), F1 (weighted ECDF of observed treated post-period outcomes), and Fte = NULL (individual treatment effect distribution is not identified for this estimator).

References

Callaway, Brantly, Tong Li, and Tatsushi Oka. “Quantile Treatment Effects in Difference in Differences Models under Dependence Restrictions and with Only Two Time Periods.” Journal of Econometrics 206(2), pp. 395-413, 2018.

ggqte

Description

Deprecated. Use autoplot() on a QTE object instead.

Usage

ggqte(
  qteobj,
  main = "",
  ylab = "QTE",
  ylim = NULL,
  ybreaks = NULL,
  xbreaks = c(0.1, 0.3, 0.5, 0.7, 0.9),
  setype = "pointwise",
  alp = qteobj$alp
)

Arguments

Value

a ggplot object

Lalonde (1986)'s NSW Dataset

Description

lalonde contains data from the National Supported Work Demonstration. This program randomly assigned applicants to the job training program (or out of the job training program). The dataset is discussed in Lalonde (1986). The experimental part of the dataset is combined with an observational dataset from the Panel Study of Income Dynamics (PSID). Lalonde (1986) and many subsequent papers (e.g. Heckman and Hotz (1989), Dehejia and Wahba (1999), Smith and Todd (2005), and Firpo (2007) have used this combination to study the effectiveness of various ‘observational’ methods (e.g. regression, Heckman selection, Difference in Differences, and propensity score matching) of estimating the Average Treatment Effect (ATE) of participating in the job training program. The idea is that the results from the observational method can be compared to results that can be easily obtained from the experimental portion of the dataset.

To be clear, the observational data combines the observations that are treated from the experimental portion of the data with untreated observations from the PSID.

Usage

data(lalonde)

Format

Four data.frames: (i) lalonde.exp contains a cross sectional version of the experimental data, (ii) lalonde.psid contains a cross sectional version of the observational data, (iii) lalonde.exp.panel contains a panel version of the experimental data, and (iv) lalonde.psid.panel contains a panel version of the observational data. Note: the cross sectional and panel versions of each dataset are identical up to their shape; in demonstrating each of the methods, it is sometimes convenient to have one form of the data or the other.

References

LaLonde, Robert. “Evaluating the Econometric Evaluations of Training Programs with Experimental Data.” The American Economics Review, pp. 604-620, 1986. @source The dataset comes from Lalonde (1986) and has been studied in much subsequent work. The qte package uses a version from the causalsens package (https://CRAN.R-project.org/package=causalsens)

Lalonde's Experimental Dataset

Description

The cross sectional verion of the experimental part of the lalonde dataset. It is loaded with all the datasets with the command data(lalonde)

Lalonde's Panel Experimental Dataset

Description

The panel verion of the experimental part of the lalonde dataset. It is loaded with all the datasets with the command data(lalonde)

Lalonde's Observational Dataset

Description

The cross sectional verion of the observational part of the lalonde dataset. It is loaded with all the datasets with the command data(lalonde)

Lalonde's Panel Observational Dataset

Description

The panel verion of the observational part of the lalonde dataset. It is loaded with all the datasets with the command data(lalonde)

lou_gt

Description

Estimates the ATT and counterfactual distribution F_0 = F_{Y(0)|D=1} for a single (g,t) cell under lagged-outcome unconfoundedness. Called internally by lou_qtt via ptetools::pte().

Usage

lou_gt(
  gt_data,
  xformula = ~1,
  lagged_outcome_cov = TRUE,
  est_method = "ipw",
  ...
)

Arguments

Value

A list from ptetools::attgt_noif with attgt (ATT) and extra_gt_returns containing F0 and F1 (weighted ECDFs of counterfactual and observed treated outcomes).

Lagged Outcome Unconfoundedness QTT

Description

Estimates the Quantile Treatment Effect on the Treated (QTT) and Average Treatment Effect on the Treated (ATT) under a lagged-outcome unconfoundedness assumption with staggered treatment adoption. The key identifying assumption is Y_{g,t}(0) \perp D \mid X, Y_{\text{pre}}, i.e., conditional on observed covariates and the pre-treatment outcome, treatment is as good as randomly assigned within each cohort-period cell.

Estimation operates at the (g,t) level: for each cohort g and post-treatment period t, a cross-sectional comparison is made between the treated group and a not-yet-treated (or never-treated) comparison group, adjusting for covariates and (optionally) the pre-treatment outcome. Group-time estimates are then aggregated to overall, dynamic, and group-specific summaries.

Three estimation methods are available:

"ipw"

Propensity-score reweighting. Control units are reweighted by \hat p(X,Y_{\text{pre}})/(1-\hat p(X,Y_{\text{pre}})) to approximate the covariate distribution of the treated group.

"or"

Outcome regression. A quantile regression model is fit on control units' post-period outcomes as a function of (X, Y_{\text{pre}}), then predicted at treated units to construct the counterfactual distribution (Melly 2006; Chernozhukov, Fernandez-Val, and Melly 2013).

"aipw"

Doubly-robust augmented IPW. Combines the propensity score and outcome models. Consistent if either model is correctly specified.

When lagged_outcome_cov = FALSE and xformula = ~1, all three methods reduce to a simple distribution comparison within each (g,t) cell, which is consistent under unconditional unconfoundedness.

The ATT analogue (without the QTT) for staggered adoption under lagged-outcome unconfoundedness is developed in Callaway (2023).

Usage

lou_qtt(
  yname,
  gname,
  tname,
  idname = NULL,
  data,
  xformula = ~1,
  lagged_outcome_cov = TRUE,
  est_method = c("ipw", "or", "aipw"),
  panel = TRUE,
  weightsname = NULL,
  control_group = "notyettreated",
  anticipation = 0,
  alp = 0.05,
  cband = TRUE,
  biters = 100,
  cl = 1,
  gt_type = c("att", "qtt"),
  probs = NULL
)

Arguments

Value

For gt_type = "att", a pte_emp_boot object. For gt_type = "qtt", a pte_qtt object with overall, group-specific, and dynamic QTT curves, bootstrap standard errors, and pointwise and uniform confidence bands.

References

Callaway, Brantly. “Policy Evaluation during a Pandemic.” Journal of Econometrics 236(2), 2023.

Melly, Blaise. “Estimation of Counterfactual Distributions Using Quantile Regression.” Working paper, University of St. Gallen, 2006.

Chernozhukov, Victor, Ivan Fernandez-Val, and Blaise Melly. “Inference on Counterfactual Distributions.” Econometrica 81(6), pp. 2205–2268, 2013.

See Also

unc_qte for the cross-sectional (non-staggered) version. cic, qdid, mdid for alternative identification strategies with staggered adoption.

Examples

data(mpdta, package = "did")

## ATT under lagged-outcome unconfoundedness (IPW with pre-period outcome)
res_att <- lou_qtt(
  yname = "lemp", gname = "first.treat", tname = "year",
  idname = "countyreal", data = mpdta,
  lagged_outcome_cov = TRUE, est_method = "ipw",
  gt_type = "att", biters = 20
)
summary(res_att)

## QTT with doubly-robust estimation
res_qtt <- lou_qtt(
  yname = "lemp", gname = "first.treat", tname = "year",
  idname = "countyreal", data = mpdta,
  lagged_outcome_cov = TRUE, est_method = "aipw",
  gt_type = "qtt", probs = seq(0.1, 0.9, 0.1), biters = 20
)
summary(res_qtt)

Mean Difference-in-Differences

Description

Computes Quantile Treatment effects on the Treated (QTT) and the Average Treatment Effect on the Treated (ATT) using the Mean Difference-in-Differences identification strategy. Handles two-period data and staggered treatment adoption uniformly. Supports both panel and repeated cross sections data.

Identification. MDiD assumes the counterfactual distribution of untreated potential outcomes is a location shift of the treated group's pre-treatment distribution. The size of the shift is the mean DiD \Delta = E[Y_{\text{post}}|D=0] - E[Y_{\text{pre}}|D=0], so Q_{Y(0),\text{post}|D=1}(\tau) = Q_{Y,\text{pre}|D=1}(\tau) + \Delta. This is stronger than parallel trends in means alone: it additionally requires that the shape of the treated group's outcome distribution is unchanged in the counterfactual. MDiD is a special case of QDiD that applies a single mean shift rather than a rank-specific distributional shift.

Covariate adjustment. When xformula is specified, the scalar shift is replaced by a unit-specific conditional mean shift \Delta(X_i) = E[Y_{\text{post}}|D=0,X_i] - E[Y_{\text{pre}}|D=0,X_i], estimated by weighted OLS. The counterfactual for treated unit i is Y_{\text{pre},i} + \Delta(X_i), and the unconditional counterfactual distribution is the empirical CDF of these values. By the law of iterated expectations, this consistently estimates F_{Y(0),\text{post}|D=1}.

Usage

mdid(
  yname,
  gname,
  tname,
  idname = NULL,
  data,
  panel = TRUE,
  xformula = ~1,
  weightsname = NULL,
  control_group = "notyettreated",
  anticipation = 0,
  alp = 0.05,
  cband = TRUE,
  biters = 100,
  cl = 1,
  ret_quantile = NULL,
  gt_type = "att",
  probs = NULL
)

Arguments

Value

For gt_type = "att", a pte_results object from ptetools. For gt_type = "qtt", a pte_qtt object with overall, group-specific, and dynamic QTT curves and bootstrap SEs.

References

Athey, Susan and Guido Imbens. “Identification and Inference in Nonlinear Difference-in-Differences Models.” Econometrica 74(2), pp. 431-497, 2006.

Thuysbaert, Bram. “Distributional Comparisons in Difference in Differences Models.” Working Paper, 2007.

Examples

data(mpdta, package = "did")

## ATT aggregated across all groups and periods
res_att <- mdid(yname = "lemp", gname = "first.treat", tname = "year",
                idname = "countyreal", data = mpdta,
                gt_type = "att", biters = 20)
summary(res_att)

## Full QTT curve at selected quantiles
res_qtt <- mdid(yname = "lemp", gname = "first.treat", tname = "year",
                idname = "countyreal", data = mpdta,
                gt_type = "qtt", probs = seq(0.1, 0.9, 0.1), biters = 20)
summary(res_qtt)

Mean Difference-in-Differences: group-time estimator

Description

Computes the MDiD ATT and counterfactual outcome distribution for a single 2x2 (pre/post x treated/control) data subset. Serves directly as the attgt_fun argument to ptetools::pte. Panel vs. repeated cross sections is detected automatically from whether the same unit ids appear in both periods.

Identification. MDiD assumes that the counterfactual distribution of untreated potential outcomes for the treated group in the post period is a location shift of the treated group's pre-period distribution:

F_{Y(0),\text{post}|D=1}(y) = F_{Y,\text{pre}|D=1}(y - \Delta)

where \Delta = E[Y_{\text{post}}|D=0] - E[Y_{\text{pre}}|D=0] is the mean DiD (the change in mean outcomes for the untreated group). The counterfactual quantile function is therefore Q_{Y(0),\text{post}|D=1}(\tau) = Q_{Y,\text{pre}|D=1}(\tau) + \Delta.

Covariate adjustment. With covariates, the scalar shift \Delta is replaced by a unit-specific conditional mean shift \Delta(X_i) = E[Y_{\text{post}}|D=0, X_i] - E[Y_{\text{pre}}|D=0, X_i], estimated by weighted OLS on the control group in each period. The counterfactual for treated pre-period unit i is Y_{\text{pre},i} + \Delta(X_i). The unconditional counterfactual distribution is the empirical CDF of these shifted values, which by the law of iterated expectations consistently estimates F_{Y(0),\text{post}|D=1}(y) = \int F_{Y,\text{pre}|D=1,X=x}(y - \Delta(x))\,dF_{X|D=1}(x).

Usage

mdid_gt(gt_data, xformula = ~1, ...)

Arguments

Value

A ptetools::attgt_noif object with the ATT estimate and, in extra_gt_returns, three objects: F1 (weighted ECDF of observed treated outcomes in the post period), F0 (weighted ECDF of counterfactual untreated outcomes for the treated group), and Fte (weighted ECDF of individual treatment effects; NULL for repeated cross sections).

References

Athey, Susan and Guido Imbens. “Identification and Inference in Nonlinear Difference-in-Differences Models.” Econometrica 74(2), pp. 431-497, 2006.

Thuysbaert, Bram. “Distributional Comparisons in Difference in Differences Models.” Working Paper, 2007.

panel.checks

Description

Validates that the panel data structure is compatible with the panel estimators in the qte package. Specifically: checks that the treated group composition is constant across all time periods, warns if covariates appear to vary over time, and stops with an informative message if the treated group is empty or changes.

Usage

panel.checks(qp)

Arguments

Value

Invisibly returns NULL. Called for its side effects (warnings and errors).

panel.qtet

Description

Deprecated. Use panel_qtt instead. panel_qtt supports staggered treatment adoption and exposes the pre_copula option for controlling how the copula is transferred across pre-treatment periods.

panel.qtet computes the Quantile Treatment Effect on the Treated (QTET) using the method of Callaway and Li (2015). This method should be used when the researcher wants to invoke a Difference in Differences assumption to identify the QTET. Relative to the other Difference in Differences methods available in the qte package, this method's assumptions are more intuitively similar to the identifying assumptions used in identifying the Average Treatment Effect on the Treated (ATT).

Additionally, this method can accommodate covariates in a more flexible way than the other Difference in Differences methods available. In order to accommodate covariates, the user should specify a vector x of covariate names. The user also may specify a method for estimating the propensity score. The default is logit.

panel.qtet can only be used in some situations, however. The method requires three periods of panel data where individuals are not treated until the last period. The data should be formatted as a panel; the names of columns containing time periods and ids for each cross sectional unit need to be passed to the method.

Usage

panel.qtet(
  formla,
  xformla = NULL,
  t,
  tmin1,
  tmin2,
  tname,
  data,
  idname,
  probs = seq(0.05, 0.95, 0.05),
  iters = 100,
  alp = 0.05,
  method = c("qr", "pscore"),
  se = TRUE,
  retEachIter = FALSE,
  pl = FALSE,
  cores = NULL,
  biters = NULL,
  cl = NULL
)

Arguments

Value

QTE object

References

Callaway, Brantly and Tong Li. “Quantile Treatment Effects in Difference in Differences Models with Panel Data.” Working Paper, 2019.

See Also

panel_qtt for the modern replacement supporting staggered adoption.

Examples

# See ?panel_qtt for the modern replacement.
## Not run: 
data(lalonde)

## Run the panel.qtet method on the experimental data with no covariates
pq1 <- panel.qtet(re ~ treat,
  t = 1978, tmin1 = 1975, tmin2 = 1974, tname = "year",
  data = lalonde.exp.panel, idname = "id", se = FALSE,
  probs = seq(0.05, 0.95, 0.05)
)
summary(pq1)

## Run the panel.qtet method on the observational data with no covariates
pq2 <- panel.qtet(re ~ treat,
  t = 1978, tmin1 = 1975, tmin2 = 1974, tname = "year",
  data = lalonde.psid.panel, idname = "id", se = FALSE,
  probs = seq(0.05, 0.95, 0.05)
)
summary(pq2)

## Run the panel.qtet method on the observational data conditioning on
## age, education, black, hispanic, married, and nodegree.
## The propensity score will be estimated using the default logit method.
pq3 <- panel.qtet(re ~ treat,
  t = 1978, tmin1 = 1975, tmin2 = 1974, tname = "year",
  xformla = ~ age + I(age^2) + education + black + hispanic + married + nodegree,
  data = lalonde.psid.panel, idname = "id", se = FALSE, method = "pscore",
  probs = seq(0.05, 0.95, 0.05)
)
summary(pq3)

pq4 <- panel.qtet(re ~ treat,
  t = 1978, tmin1 = 1975, tmin2 = 1974, tname = "year",
  xformla = ~ age + I(age^2) + education + black + hispanic + married + nodegree,
  data = lalonde.psid.panel, idname = "id", se = FALSE, method = "qr",
  probs = seq(0.05, 0.95, 0.05)
)
summary(pq4)

## End(Not run)

Panel QTT (Callaway-Li 2019)

Description

Computes Quantile Treatment Effects on the Treated (QTT) and the Average Treatment Effect on the Treated (ATT) using the three-period panel identification strategy of Callaway and Li (2019). Handles two-period (one post + two pre-treatment periods) and staggered treatment adoption via ptetools. Requires panel data for both groups.

Identification. Under a copula stability assumption and distributional parallel trends on changes, the counterfactual distribution F_{Y(0)^{\text{post}}|D=1} is recovered from three periods of panel data without requiring rank invariance.

pre_copula. Controls which pre-treatment periods are used as the copula-transfer base for post-treatment cells (g, g+e):

"long" (default)

pre2 = 2*(g - anticipation) - (g+e) - 2, matching the copula window to the event horizon e. Cells where pre2 does not exist in the data are excluded from aggregation with two-step weight renormalization.

"short"

pre2 = g - anticipation - 2, always anchored at treatment onset.

Pre-test placebo cells always use the sliding base regardless of pre_copula.

Usage

panel_qtt(
  yname,
  gname,
  tname,
  idname,
  data,
  xformula = ~1,
  weightsname = NULL,
  control_group = "notyettreated",
  anticipation = 0,
  alp = 0.05,
  cband = TRUE,
  biters = 100,
  cl = 1,
  gt_type = "att",
  probs = NULL,
  pre_copula = "long"
)

Arguments

Value

For gt_type = "att", a pte_emp_boot object. For gt_type = "qtt", a pte_qtt object.

References

Callaway, Brantly and Tong Li. “Quantile Treatment Effects in Difference-in-Differences Models with Panel Data.” Quantitative Economics 10(4), pp. 1579-1618, 2019.

See Also

cic, qdid, mdid, ddid

Examples

data(mpdta, package = "did")

## Panel QTT with rolling pre-period copula (default pre_copula = "long")
res <- panel_qtt(yname = "lemp", gname = "first.treat", tname = "year",
                 idname = "countyreal", data = mpdta,
                 gt_type = "qtt", probs = seq(0.1, 0.9, 0.1), biters = 20)
summary(res)

Panel QTT: group-time estimator (Callaway-Li 2019)

Description

Computes the panel QTT and counterfactual outcome distribution for a single (g,t) cell using the three-period copula-stability estimator of Callaway and Li (2019). Serves directly as the attgt_fun argument to ptetools::pte.

Identification. Under copula stability

C(F_{Y^{\text{pre2}}|D=1},\, F_{\Delta Y^{\text{pre}}|D=1}) = C(F_{Y^{\text{pre1}}(0)|D=1},\, F_{\Delta Y^{\text{post}}(0)|D=1})

and distributional parallel trends on changes

F_{\Delta Y^{\text{post}}(0)|D=1} = F_{\Delta Y^{\text{ctrl}}}

the counterfactual outcome for each treated unit i is kcf_i = L_i + C_i, where L_i = Q_{Y^{\text{pre1}}|D=1}(u_i) is the treated pre1 quantile at rank u_i = F_{Y^{\text{pre2}}|D=1}(Y^{\text{pre2}}_i) (the Rosenblatt transform), and C_i = Q_{\Delta Y^{\text{ctrl}}}(v_i) is the control change at rank v_i = F_{\Delta Y^{\text{pre}}|D=1}(\Delta Y^{\text{pre}}_i). The goal is distributional: \{kcf_i\} is a sample from F_{Y(0)^{\text{post}}|D=1}, not individual counterfactuals.

Panel data required for both groups. Three periods for treated (pre2, pre1, post) and two for control (pre1, post).

Usage

panel_qtt_gt(gt_data, xformula = ~1, ...)

Arguments

Value

A ptetools::attgt_noif object with att and, in extra_gt_returns, F0 (counterfactual ECDF), F1 (observed post ECDF), and Fte (individual-effect ECDF).

References

Callaway, Brantly and Tong Li. “Quantile Treatment Effects in Difference-in-Differences Models with Panel Data.” Quantitative Economics 10(4), pp. 1579-1618, 2019.

QTT Aggregation for pre_copula = "long"

Description

Custom aggte_fun for ptetools::pte that handles the two-step weight renormalization needed when pre_copula = "long": some (g,t) cells are structurally uncomputable (their pre2 does not exist in the data), and those cells must be excluded from aggregation with proper weight redistribution.

Two-step weights (overall):

1. Identify surviving groups (those with at least one valid post-treatment cell); renormalize p_g among those groups only.

2. Within each surviving group, assign equal weight p_g / |\text{valid cells for } g| to each valid post-treatment cell.

Dynamic (event-study) weights: for each event time e, renormalize p_g among groups where (g, g+e) is valid.

Error behaviour: if a structurally valid cell returns NA att, the function errors immediately — such NAs indicate a bug in panel_qtt_gt, not a structural limitation.

Usage

panel_qtt_long_agg(attgt.list, ptep, extra_gt_returns)

Arguments

Value

A list with overall_results, dyn_results, group_results, attgt_results, F0_overall, F1_overall — matching the structure returned by ptetools::qtt_pte_aggregations.

panelize.data

Description

get data in correct format for using panel methods in qte package

Usage

panelize.data(data, idname, tname, t, tmin1, tmin2 = NULL)

Arguments

Value

data.frame

plot.QTE

Description

Plots a QTE object using autoplot.QTE.

Usage

## S3 method for class 'QTE'
plot(x, cband = TRUE, ylab = "QTE", ...)

Arguments

Value

invisibly returns the ggplot object.

Print summary.QTE

Description

Prints a summary.QTE object.

Usage

## S3 method for class 'summary.QTE'
print(x, ...)

Arguments

Value

None. Called for its side effect of printing.

Quantile Difference-in-Differences

Description

Computes Quantile Treatment effects on the Treated (QTT) and the Average Treatment Effect on the Treated (ATT) using the Quantile Difference-in-Differences identification strategy of Athey and Imbens (2006). Handles two-period data and staggered treatment adoption uniformly. Supports both panel and repeated cross sections data.

Usage

qdid(
  yname,
  gname,
  tname,
  idname = NULL,
  data,
  panel = TRUE,
  xformula = ~1,
  weightsname = NULL,
  control_group = "notyettreated",
  anticipation = 0,
  alp = 0.05,
  cband = TRUE,
  biters = 100,
  cl = 1,
  ret_quantile = NULL,
  gt_type = "att",
  probs = NULL
)

Arguments

Value

For gt_type = "att", a pte_results object from ptetools. For gt_type = "qtt", a pte_qtt object with overall, group-specific, and dynamic QTT curves and bootstrap SEs.

References

Athey, Susan and Guido Imbens. “Identification and Inference in Nonlinear Difference-in-Differences Models.” Econometrica 74(2), pp. 431-497, 2006.

Examples

data(mpdta, package = "did")

## ATT aggregated across all groups and periods
res_att <- qdid(yname = "lemp", gname = "first.treat", tname = "year",
                idname = "countyreal", data = mpdta,
                gt_type = "att", biters = 20)
summary(res_att)

## Full QTT curve at selected quantiles
res_qtt <- qdid(yname = "lemp", gname = "first.treat", tname = "year",
                idname = "countyreal", data = mpdta,
                gt_type = "qtt", probs = seq(0.1, 0.9, 0.1), biters = 20)
summary(res_qtt)

Quantile Difference-in-Differences: group-time estimator

Description

Computes the QDiD ATT and counterfactual outcome distribution for a single 2x2 (pre/post x treated/control) data subset. Serves directly as the attgt_fun argument to ptetools::pte. Panel vs. repeated cross sections is detected automatically from whether the same unit ids appear in both periods.

Usage

qdid_gt(gt_data, xformula = ~1, ...)

Arguments

Value

A ptetools::attgt_noif object with the ATT estimate and, in extra_gt_returns, three objects: F1 (weighted ECDF of observed treated outcomes in the post period), F0 (weighted ECDF of counterfactual untreated outcomes for the treated group), and Fte (weighted ECDF of individual treatment effects; NULL for repeated cross sections).

References

Athey, Susan and Guido Imbens. “Identification and Inference in Nonlinear Difference-in-Differences Models.” Econometrica 74(2), pp. 431-497, 2006.

setupData

Description

setupData extracts treated/untreated subsets, ECDFs, and auxiliary vectors from a QTEparams object and injects them into the caller's environment via assign(..., envir=parent.frame()). This side-effectful pattern is intentional — all compute.* functions rely on the variables created here being available in their local scope.

Usage

setupData(qteParams)

Arguments

Value

Invisibly returns NULL. The function's effect is the assignment of data objects into the calling environment.

Summary

Description

summary.QTE summarizes a QTE object, returning formatted data frames for the overall ATE and the QTE table suitable for printing.

Usage

## S3 method for class 'QTE'
summary(object, ...)

Arguments

Value

A summary.QTE object (a list with overall_ate and qte_table data frames).

Three-Period Subset for Panel QTT

Description

Custom subset_fun for ptetools::pte that pulls three time periods for each (g,t) cell: pre2, pre1 = g - anticipation - 1, and post = tp. How pre2 is chosen depends on pre_copula:

"long" (default)

pre2 = 2*(g - anticipation) - tp - 2, so the copula-transfer window matches the event horizon e = tp - (g - anticipation). Cells where this pre2 does not exist in the data return empty data and panel_qtt_gt returns NA.

"short"

pre2 = g - anticipation - 2 (fixed at treatment onset regardless of e).

For pre-treatment placebo cells (tp < g - anticipation), the base always slides backwards regardless of pre_copula: pre2 = tp - 2, pre1 = tp - 1. panel_qtt() sets required_pre_periods = 2 so that the minimum tp in tlist is the third period, guaranteeing tp - 2 is always a valid period.

Usage

three_period_subset(
  data,
  g,
  tp,
  control_group = "notyettreated",
  anticipation = 0,
  pre_copula = "long",
  ...
)

Arguments

Value

A list with elements gt_data, n1, disidx.

unc_qte

Description

Estimates the Quantile Treatment Effect (QTE) or Quantile Treatment Effect on the Treated (QTT) under unconfoundedness, also known as selection on observables. The key identifying assumption is (Y(0), Y(1)) \perp D \mid X, i.e., potential outcomes are independent of treatment conditional on covariates X.

Three estimation methods are available via est_method:

"ipw"

Propensity-score reweighting (Firpo 2007). The propensity score p(X) = P(D=1|X) is estimated by logit or probit and used to reweight the sample so that the covariate distributions of the treated and untreated groups match. For the QTE, both groups are reweighted toward the population distribution; for the QTT, only the untreated group is reweighted toward the treated covariate distribution.

"or"

Outcome regression via quantile regression inversion. rq is fit on a dense internal grid of \tau values, yielding a conditional quantile function Q_{Y|X,D=j}(\tau) for each arm j. The marginal distribution is recovered by averaging conditional quantile functions over the empirical covariate distribution (Melly 2006; Chernozhukov, Fernandez-Val, and Melly 2013).

"aipw"

Doubly-robust augmented IPW. Combines the propensity score model with the conditional quantile outcome model. The CDF estimator is consistent if either the propensity score or the outcome model is correctly specified (semiparametric efficiency when both are correct).

When xformla = ~1 (the default), all three methods reduce to simple quantile differences between the treated and untreated groups, which is consistent under unconditional unconfoundedness. Covariates are required for covariate-adjusted estimation.

Standard errors and uniform confidence bands are computed via the empirical bootstrap. Setting biters = 0 is planned for a future version to skip inference and return point estimates only.

Usage

unc_qte(
  yname,
  dname,
  data,
  xformla = ~1,
  weightsname = NULL,
  probs = seq(0.05, 0.95, 0.05),
  alp = 0.05,
  biters = 100,
  cband = TRUE,
  boot_type = "empirical",
  method = c("logit", "probit"),
  est_method = c("ipw", "or", "aipw"),
  target = c("qte", "qtt"),
  cl = 1
)

Arguments

Value

An object of class QTE containing:

qte

numeric vector of estimated QTE (or QTT) at each element of probs.

ate

estimated ATE (or ATT when target = "qtt").

qte.se

bootstrap standard errors for qte.

qte.lower, qte.upper

confidence interval bounds for qte; uniform when cband = TRUE, pointwise otherwise.

ate.se, ate.lower, ate.upper

SE and CI for ate.

probs

the probs vector passed by the user.

pscore.reg

fitted propensity score glm object, or NULL when est_method = "or" or xformla = ~1.

Use summary() to print a formatted table and plot() to display the QTE curve with confidence bands.

References

Firpo, Sergio. “Efficient Semiparametric Estimation of Quantile Treatment Effects.” Econometrica 75(1), pp. 259–276, 2007.

Melly, Blaise. “Estimation of Counterfactual Distributions Using Quantile Regression.” Working paper, University of St. Gallen, 2006.

Chernozhukov, Victor, Ivan Fernandez-Val, and Blaise Melly. “Inference on Counterfactual Distributions.” Econometrica 81(6), pp. 2205–2268, 2013.

Examples

data(lalonde)

## IPW, no covariates (simple quantile differences)

q1 <- unc_qte(yname = "re78", dname = "treat", data = lalonde.psid,
              biters = 20, probs = seq(0.05, 0.95, 0.05))
summary(q1)
plot(q1)


## OR with covariates, QTE

xf <- ~ age + I(age^2) + education + black + hispanic + married + nodegree
q2 <- unc_qte(yname = "re78", dname = "treat", data = lalonde.psid,
              xformla = xf, est_method = "or",
              biters = 20, probs = seq(0.05, 0.95, 0.05))
summary(q2)


## AIPW with covariates, QTT

q3 <- unc_qte(yname = "re78", dname = "treat", data = lalonde.psid,
              xformla = xf, est_method = "aipw", target = "qtt",
              biters = 20, probs = seq(0.05, 0.95, 0.05))
summary(q3)

Weighted type-1 quantile

Description

Smallest y with weighted CDF >= p. Uses a small numerical tolerance on the comparison so that a p landing exactly on a floating-point rounding boundary (common with uniform weights, e.g. 1/n) picks the intended order statistic instead of flipping based on last-bit differences in summation across platforms.

Usage

wquant(y_vec, w_vec, probs)

Arguments

Value

numeric vector, same length as probs.