truncreg {truncreg} | R Documentation |
Estimation of models with truncated explanatory variables by maximum likelihood
truncreg(formula, data, subset, weights, na.action, point = 0, direction = "left", ...) ## S3 method for class 'truncreg' print(x, digits = max(3, getOption("digits") - 2), width = getOption("width"), ...) ## S3 method for class 'truncreg' summary(object, ...) ## S3 method for class 'summary.truncreg' print(x, digits = max(3, getOption("digits") - 2), width = getOption("width"), ...) ## S3 method for class 'truncreg' logLik(object, ...) ## S3 method for class 'truncreg' vcov(object, ...) ## S3 method for class 'truncreg' residuals(object, ...) ## S3 method for class 'truncreg' fitted(object, ...)
x, object |
an object of class |
formula |
a symbolic description of the model to be estimated, |
data |
the data, |
subset |
an optional vector specifying a subset of observations, |
weights |
an optional vector of weights, |
na.action |
a function which indicates what should happen when
the data contains ' |
point |
the value of truncation (the default is 0), |
direction |
the direction of the truncation, either |
digits |
the number of digits, |
width |
the width of the printing, |
... |
further arguments. |
The model is estimated with the maxLik
package and the
Newton-Raphson method, using analytic gradient and hessian.
An object of class "truncreg"
, a list with elements:
coefficients |
the named vector of coefficients, |
vcov |
the variance matrix of the coefficients, |
fitted.values |
the fitted values, |
logLik |
the value of the log-likelihood, |
gradient |
the gradient of the log-likelihood at convergence, |
model |
the model frame used, |
call |
the matched call, |
est.stat |
some information about the estimation (time used, optimisation method), |
Yves Croissant
Hausman, J.A. and D.A. Wise (1976) “The evaluation of results from truncated samples: the New-Jersey negative invome tax experiment”, Annals of Economic ans Social Measurment, 5, pp.421–45.
Hausman, J.A. and D.A. Wise (1976) “Social experimentation, truncated distributions and efficient estimation”, Econometrica, 45, pp.421–5.
## Simulate a data.frame n <- 10000 sigma <- 4 alpha <- 2 beta <- 1 x <- rnorm(n,0,2) eps <- rnorm(n) y <- alpha+beta*x+eps*sigma d <- data.frame(y = y, x = x) ## Use a truncated subsample dl1 <- subset(d, y>1) ## Use truncreg to estimate consistently the model truncreg(y~x, dl1, point = 1, direction = "left")