smoothGel {gmm4}R Documentation

A kernel smoothing utility for "gmmModels" classes

Description

It either generates the optimal bandwidth and kernel weights when the object is a GMM model, or the smoothed moments when the object is a GEL model.

Usage

smoothGel(object, theta=NULL) 

Arguments

object

An object of class "gmmModels" or "gelModels".

theta

An optional vector of coefficients. For "gmmModels", it is the coefficient used to obtain the optimal bandwidth. If NULL, it is obtained using modelFit with the identity matrix as weights. For "gelModels", the coefficient is require since the function returns the smoothed moments at a given vector of coefficients.

Value

A list which contains:

k

2\times 1 vector of scaling factors used for GEL asymptotics. See Anatolyev (2005).

w

The kernel weights as an object of class "tskernel". See kernapply.

bw

A numeric bandwidth.

kernel

A character specifying th type of kernel used for smoothing

smoothx

Only when the object is of class "gelModels", a matrix of smoothed moments

References

Anatolyev, S. (2005), GMM, GEL, Serial Correlation, and Asymptotic Bias. Econometrica, 73, 983-1002.

Kitamura, Yuichi (1997), Empirical Likelihood Methods With Weakly Dependent Processes. The Annals of Statistics, 25, 2084-2102.

Smith, R.J. (2011), GEL Criteria for Moment Condition Models. Econometric Theory, 27(6), 1192–1235.

Examples

data(simData)
theta <- c(beta0=1,beta1=2)

## A linearGmm
model1 <- gmmModel(y~x1, ~z1+z2, data=simData,vcov="HAC",vcovOptions=list(kernel="Bartlett"))

### get the bandwidth
### Notice that the kernel name is the not the same
### That's because a Truncated kernel for smoothing
### lead to a Bartlett kernel for the HAC of the moments
### See Smith (2011)
smoothGel(model1)


### The GEL model contains the info when it is created

model2 <- gmmToGel(model1, "EL")
model2@wSpec

smoothGel(model2, theta)$smoothx[1:5,]


[Package gmm4 version 0.0-2 Index]