GAUSS code for FMLS
Begoña Eguía* http://www.ehu.es/~euzdirec/dpto/begona.htm
Facultad de Ciencias Económicas y Empresariales
Universidad del País Vasco

This code is provided gratis without any performance warrantee.

Here I describe a Gauss program that can be used to obtain the Fully Modified
Least Squared (FMLS) estimators of models whose regressors are random walks
with a drift.  There are lots of statistical and econometric applications
containing subroutines to solve specific problems such as the estimation by
ordinary least squares or the testing of unit roots. As far as we know,
however, there is no program publicly available solving this specific
estimation method. 

To this aim I have built a program in the Gauss environment, whose lines of
code are introduced in fmls.gau. Gauss is a program supporting many features of
interest to econometricians. My purpose is to give ease to the researcher who
is working with any data set and who wants to run regressions that have to be
estimated by FMLS. So, it can be useful in several branches of applied
economics.

Data used in Eguia, B. and C. A. Echevarria (2001), 
ftp://ftp.fedea.es/pub/eee/eee117.pdf
Population Age Structure and Private Consumption in Spain 
(Estructura de Edad Poblacional y Consumo Privado en Espana)",
are in ASCII format in data.txt file.

One firstly must get an understandable data file for Gauss. So we must use the
program to turn the original data file into a file that can be read by Gauss.
The content of this program file is written in make.gau. Upon running this
program file, two new files will be created: data.dat and data.dht (the data
set in Gauss format) 

Secondly, we must write a second program file. This one will have the necessary
instructions to estimate the coefficients of the model using FMLS. The lines of
code are in fmls.gau.


* Facultad de Ciencias Económicas y Empresariales.
Universidad del País Vasco.  Avda.
Lehendakari Agirre 83, 48015 Bilbao.  Spain.
E-mail: mailto:ebpegpeb@bs.ehu.es?subject=FMLS

See Hansen, B. E. and P. C. B. Phillips (1990), “Estimation and Inference in
Models of Cointegration: A Simulation Study”, Advances in Econometrics, Vol. 8,
pp. 225-248, Jai Press, Inc.: London; and Phillips, P. C. B. and B. E. Hansen
(1990), “Statistical Inference in Instrumental Variables Regression with I(1)
Process”, Review of Economic Studies 57, pp. 99-125.