lrtest.systemfit {systemfit}R Documentation

Likelihood Ratio test for Equation Systems

Description

Perform a Likelihood Ratio test to test linear restrictions when estimating an equation system.

Usage

lrtest.systemfit( resultc, resultu )

Arguments

resultc an object of type systemfit.system that contains the results of the restricted estimation.
resultu an object of type systemfit.system that contains the results of the unconstrained estimation.

Details

At the moment only the LR test for SUR models is implemented.

This test calculates the likelihood ratio value by calculating the estimated residual covariance matrix hat{Σ} by the maximum likelihood formula hat{σ}_{ij} = (hat{e}_i' hat{e}_j) / T (no matter which formula is used in the estimation).

Value

lrtest.sur.systemfit returns a three values:

lr the empirical likelihood ratio value.
p the p-value of a chi^2-test.
df the degrees of freedom of the test (= number of restrictions).

Author(s)

Arne Henningsen (http://www.arne-henningsen.de)

References

Greene, W. H. (2002) Econometric Analysis, Fifth Edition, Prentice Hall.

See Also

systemfit

Examples

## Not run: library( systemfit )
data( kmenta )
demand <- q ~ p + d
supply <- q ~ p + f + a
labels <- list( "demand", "supply" )
system <- list( demand, supply )

## unconstrained SUR estimation
fitsur <- systemfit("SUR", system, labels, data=kmenta )
print( fitsur )

## SUR estimation with 2 restrictions
Rrestr <- matrix(0,2,7)
qrestr <- matrix(0,2,1)
Rrestr[1,3] <-  1
Rrestr[1,7] <- -1
Rrestr[2,2] <- -1
Rrestr[2,5] <-  1
qrestr[2,1] <-  0.5
fitsur2 <- systemfit("SUR", system, labels, data=kmenta,
                      R.restr=Rrestr, q.restr=qrestr )
print( fitsur2 )

## perform LR-test
lrtest.systemfit( fitsur2, fitsur )
[Package Contents]