lprobust implements local polynomial point estimators with robust bias-corrected confidence intervals and inference procedures developed in Calonico, Cattaneo and Farrell (2016a). It also computes alternative estimation and inference procedures available in the literature.
For more details, and related Stata and R packages useful for empirical analysis, visit https://sites.google.com/site/rdpackages/
lprobust(y, x, c, p = 1, q = 2, deriv = 0,
h = NULL, b = NULL, rho = NULL, kernel = "epa", bwselect = "mse", scaleregul = 1,
vce = "nn", nnmatch = 3, level = 95, all = FALSE, subset = NULL)is the dependent variable.
is the independent variable.
specifies the evalution point in x.
specifies the order of the local-polynomial used to construct the point-estimator; default is p = 1 (local linear regression).
specifies the order of the local-polynomial used to construct the bias-correction; default is q = 2 (local quadratic regression).
specifies the order of the derivative of the regression functions to be estimated. Default is deriv=0
specifies the main bandwidth used to construct the LPR point estimator. If not specified, bandwidth h is computed by the companion command lpbwselect.
specifies the bias bandwidth used to construct the bias-correction estimator. If not specified, bandwidth b is computed by the companion command lpbwselect.
specifies the value of rho, so that the bias bandwidth b equals h/rho. Default is rho = 1 if h is specified but b is not.
is the kernel function used to construct the local-polynomial estimator(s). Options are triangular (default option), epanechnikov and uniform.
specifies the bandwidth selection procedure to be used. By default it computes both h and b, unless rho is specified, in which case it only computes h and sets b=h/rho.
specifies scaling factor for the regularization term added to the denominator of the bandwidth selectors. Setting scaleregul = 0 removes the regularization term from the bandwidth selectors; default is scaleregul = 1.
specifies the procedure used to compute the variance-covariance matrix estimator. Options are:
nn for heteroskedasticity-robust nearest neighbor variance estimator with nnmatch the (minimum) number of neighbors to be used.
hc0 for heteroskedasticity-robust plug-in residuals variance estimator without weights.
hc1 for heteroskedasticity-robust plug-in residuals variance estimator with hc1 weights.
hc2 for heteroskedasticity-robust plug-in residuals variance estimator with hc2 weights.
hc3 for heteroskedasticity-robust plug-in residuals variance estimator with hc3 weights.
Default is vce=nn.
to be combined with for vce=nn for heteroskedasticity-robust nearest neighbor variance estimator with nnmatch indicating the minimum number of neighbors to be used. Default is nnmatch=3
sets the confidence level for confidence intervals; default is level = 95.
if specified, lprobust reports three different procedures:
(i) conventional LPR estimates with conventional standard errors.
(ii) bias-corrected estimates with conventional standard errors.
(iii) bias-corrected estimates with robust standard errors.
an optional vector specifying a subset of observations to be used.
cutoff value.
sample size used.
overall sample size.
order of the polynomial used for estimation of the regression function.
order of the polynomial used for estimation of the bias of the regression function.
bandwidth used for estimation of the regression function.
bandwidth used for estimation of the bias of the regression function estimator.
vector containing conventional and bias-corrected local-polynomial estimates.
vector containing conventional and robust standard errors of the local-polynomial estimates.
vector containing the p-values associated with conventional, bias-corrected and robust local-polynomial estimates.
matrix containing the confidence intervals associated with conventional, bias-corrected and robust local-polynomial estimates.
Calonico, S., M. D. Cattaneo, and M. H. Farrell. 2016. On the Effect of Bias Estimation on Coverage Accuracy in Nonparametric Inference. Working Paper. http://www-personal.umich.edu/~cattaneo/papers/Calonico-Cattaneo-Farrell_2016_JASA.pdf.
Calonico, S., M. D. Cattaneo, M. H. Farrell, and R. Titiunik. 2016a. Regression Discontinuity Designs using Covariates. Working Paper. http://www-personal.umich.edu/~cattaneo/papers/Calonico-Cattaneo-Farrell-Titiunik_2016_wp.pdf.
Calonico, S., M. D. Cattaneo, M. H. Farrell, and R. Titiunik. 2016b. rdrobust: Software for Regression Discontinuity Designs. Working Paper. http://www-personal.umich.edu/~cattaneo/papers/Calonico-Cattaneo-Farrell-Titiunik_2016_Stata.pdf.
Calonico, S., M. D. Cattaneo, and R. Titiunik. 2014a. Robust Nonparametric Confidence Intervals for Regression-Discontinuity Designs. Econometrica 82(6): 2295-2326. http://www-personal.umich.edu/~cattaneo/papers/Calonico-Cattaneo-Titiunik_2014_ECMA.pdf.
Calonico, S., M. D. Cattaneo, and R. Titiunik. 2014b. Robust Data-Driven Inference in the Regression-Discontinuity Design. Stata Journal 14(4): 909-946. http://www-personal.umich.edu/~cattaneo/papers/Calonico-Cattaneo-Titiunik_2014_Stata.pdf.
Calonico, S., M. D. Cattaneo, and R. Titiunik. 2015b. rdrobust: An R Package for Robust Nonparametric Inference in Regression-Discontinuity Designs. R Journal 7(1): 38-51. http://www-personal.umich.edu/~cattaneo/papers/Calonico-Cattaneo-Titiunik_2015_R.pdf.
# NOT RUN {
x<-runif(1000,-1,1)
y<-5+3*x+rnorm(1000)
lprobust(y,x, c=0)
# }
Run the code above in your browser using DataLab