Umeå Economic Studies, Department of Economics, Umeå University
No 472:
Forecasting based on Very Small Samples and Additional Non-Sample Information
Kurt Brännäs ()
and Jörgen Hellström ()
Abstract: Generalized method of moments estimation and forecasting
is introduced for very small samples when additional non-sample information
is available. Small simulation experiments are conducted for the linear
model with errors-in-variables and for a Poisson regression model. Two
empirical illustrations are included. One is based on Ukrainian imports and
the other on private schools in a Swedish county.
Keywords: Generalized method of moments; additional information; forecasting; Ukrainian imports; private schools; (follow links to similar papers)
JEL-Codes: C22; C53; C82; F17; I20; (follow links to similar papers)
15 pages, August 21, 1998
Before downloading any of the electronic versions below
you should read our statement on
copyright.
Download GhostScript
for viewing Postscript files and the
Acrobat Reader for viewing and printing pdf files.
Full text versions of the paper:
DownloadAsset.action?contentId=127148&languageId=3&assetKey=ues472 
Download Statistics
- This paper is published as:
-
Brännäs, Kurt and Jörgen Hellström, (2006), 'Forecasting based on Very Small Samples and Additional Non-Sample Information' in Liski, Erkki P, Jarkko isotalo, Jarmo Niemelä, Simo Puntanen and George P H Styan (eds.) Festschrift for tarmo Pukkila on his 60th Birthday., chapter 3, pages 63-77, University of Tampere.
Questions (including download problems) about the papers in this series should be directed to Kjell-Göran Holmberg ()
Report other problems with accessing this service to Sune Karlsson ()
or Helena Lundin ().
Programing by
Design by Joachim Ekebom
