frmhet (version 1.1.3)

frmhet.reset: RESET Test for Fractional Regression Models under Neglected Heterogeneity

Description

frmhet.reset is used to test the specification of fractional regression models estimated by GMMx or LINx.

Usage

frmhet.reset(object, lastpower.vec = 3, version = "Wald", table = T, ...)

Arguments

object

an object containing the results of an frmhet command.

lastpower.vec

a numeric vector containing the maximum powers of the linear predictors to be used in RESET tests.

version

a vector containing the test versions to use. Available options: Wald (the default) and LM (only available for GMMx).

table

a logical value indicating whether a summary table with the test results should be printed.

...

Arguments to pass to nlminb, which is used to estimate the model under the alternative hypothesis when version is equal to "Wald" and the null model was estimated by GMMx.

Value

frm.reset returns a named vector with the test results.

Details

frmhet.reset applies the RESET test statistic to fractional regression models estimated via frmhet using the options GMMx or LINx. frmhet.reset may be used to test simultaneously the validity of the link specification and the transformation applied to the response variable by each estimator. It is taken into account the option that was chosen for computing standard errors in the model under evaluation. See Ramalho and Ramalho and Ramalho (2016) for details.

References

Ramalho, E.A. and J.J.S. Ramalho (2016), "Moment-based estimation of nonlinear regression models with boundary outcomes and endogeneity, with applications to nonnegative and fractional responses", Econometric Reviews, forthcoming (DOI: 10.1080/07474938.2014.976531).

See Also

frmhet, for fitting fractional regression models under unobserved heterogeneity. frmhet.pe, for computing partial effects.

Examples

N <- 250
u <- rnorm(N)

X <- cbind(rnorm(N),rnorm(N))
dimnames(X)[[2]] <- c("X1","X2")

Z <- cbind(rnorm(N),rnorm(N),rnorm(N))
dimnames(Z)[[2]] <- c("Z1","Z2","Z3")

y <- exp(X[,1]+X[,2]+u)/(1+exp(X[,1]+X[,2]+u))

res <- frmhet(y,X,type="GMMx",table=FALSE)

#LM and Wald versions of the RESET test, based on 1 or 2 fitted powers of xb
frmhet.reset(res,2:3,c("Wald","LM"))

## See the website http://evunix.uevora.pt/~jsr/FRM.htm for more examples.