Tobit regression {Rfast2}

Tobit regression

Description

Tobit regression.

Usage

tobit.reg(y, x, ylow = 0, full = FALSE, tol = 1e-07, maxiters = 100) 

Arguments

y

The dependent variable; a numerical vector with values.

x

A matrix with the data, where the rows denote the samples (and the two groups) and the columns are the variables. This can be a matrix or a data.frame (with factors).

ylow

The lowest value below which nothing is observed. The cut-off value.

full

If this is FALSE, the coefficients and the log-likelihood will be returned only. If this is TRUE, more information is returned.

tol

The tolerance value to terminate the Newton-Raphson algorithm.

maxiters

The max number of iterations that can take place in each regression.

Details

The tobit regression model is fitted.

Value

When full is FALSE a list including:

be

The estimated regression coefficients.

s

The estimated scale parameter.

loglik

The log-likelihood of the model.

iters

The number of iterations required by Newton-Raphson.

When full is TRUE a list including:

info

The estimated theta, regression coefficients, their standard error, their Wald test statistic and their p-value.

loglik

The log-likelihood.

iters

The number of iterations required by Newton-Raphson.

Author(s)

Michail Tsagris.

R implementation and documentation: Michail Tsagris [e-mail].

References

Tobin James (1958). Estimation of Relationships for Limited Dependent Variables. Econometrica, 26(1): 24–36.

https://en.wikipedia.org/wiki/Tobit_model

See Also

hp.reg, ztp.reg, censweibull.mle, censpois.mle

Examples

x <- rnorm(100)
y <- rnorm(100)
y[y < 0] <- 0
a <- tobit.reg(y, x, full = TRUE)