etreg: etreg (Endogenous treatment effect model)

In bolimorales/RegUtils: Tools For Model Regressions

Description

etreg fits an average treatment effect (ATE) linear regression model augmented with an endogenous treatment variable.

Usage

etreg(formula, treat, data, subset, na.action,
contrasts = NULL, model = TRUE, y = TRUE, x = FALSE,
method = "NR", ...)

Arguments

formula	a symbolic description for the model to be estimated,
treat	a symbolic description for the treatment model to be estimated,
data	a data.frame,
subset	see lm for "alm", a character or numeric vector indicaing asubset of the table of coefficient to be printed for "print.summary.alm",
na.action	a function which indicates what should happen when the data contain NAs. The default is set by the na.action setting of options, and is na.fail if that is unset. The ‘factory-fresh’ default is na.omit. Another possible value is NULL, no action. Value na.exclude can be useful.
method	maximisation method (from maxLik package), currently either "NR" (for Newton-Raphson), "BFGS" (for Broyden-Fletcher-Goldfarb-Shanno), "BFGSR" (for the BFGS algorithm implemented in R), "BHHH" (for Berndt-Hall-Hall-Hausman), "SANN" (for Simulated ANNealing), "CG" (for Conjugate Gradients), or "NM" (for Nelder-Mead). Lower-case letters (such as "nr" for Newton-Raphson) are allowed. If missing, a suitable method is selected automatically. See maxLik
...	further arguments.

Details

The endogenous treatment-regression model is composed of an equation for the outcome: yj = xj.Beta + delta.tj + uj and an equation for the endogenous treatmen: tj = 1 (if wj.gamma + ej > 0) | 0 (otherwise) where xj are the covariates used to model the outcome, wj are the covariates used to model treatment assignment, and the error terms uj and ej are bivariate normal with mean zero and covariance matrix: |sigma^2 rho.sigma | |rho.sigma 1 |

Value

object of class 'etrg' which inherits from class 'maxLik'. Components are identical to those of class 'maxLik', see maxLik.

References

Wooldridge, J. M. (2010). Econometric Analysis of Cross Section and Panel Data. 2nd ed. Cambridge. MIT Press.

See Also

See Also as maxLik

Examples

data(Mroz, package="car")
Mroz$wcb = as.integer(Mroz$wc)
fit1 = etreg(inc~age+wcb+k618+k5+lfp,wcb~hc+age,data=Mroz)
summary(fit1, robust=TRUE)

bolimorales/RegUtils documentation built on May 12, 2019, 11:33 p.m.