ELFCALC Procedure

@ELFCalc computes the empirical likelihood for a set of moment conditions, that is, it finds the maximum of

\(\sum\limits_i {\log {w_i}} \)

subject to

(a) \(\sum\limits_i {{w_i}} = 1\) and

(b) \(\sum\limits_i {{w_i}{f_i}} = 0\)

where the \(f\) are the moment conditions. See Imbens(2002). Note that, in practice, the input moment conditions will depend upon parameters to be estimated, so this is used to evaluate the empirical likelihood for a test set of parameters. You would typically have to use this inside a FIND calculation to estimate the model itself.

@ELFCalc( options )start end

# list of series with moment conditions

Parameters

start, end

range over which to do calculation. By default, the common range of the list of series.

Options

ITERS=maximum number of iterations [40]

SUBITERS=maximum number of subiterations [10]

CVCRIT=convergence criterion on Lagrange multipliers [1.e-6]

TRACE/[NOTRACE]

W=(output) SERIES of weights