Multicollinearity and Measurement Error in Econometric Financial Modelling
Christopher Green and
The Manchester School of Economic & Social Studies, 1989, vol. 57, issue 4, 357-69
Econometric financial modeling has produced a range of counterintuitive results. Estimated interest elasticities are invariably smaller than intuition would suggest and, in many cases, have the opposite sign to that predicted by theory. This paper considers the possibility that such results may be due in part to the interaction between multicollinearity and measurement error involving the interest rates in asset demand functions. Usng a two variable example, we focus on inconsistencies in the estimation of the own rate and cross rate coefficients. For the own rate coefficient, the sign of the inconsistency conforms with intuition, producing an estimated elasticity which is "too small." For the cross rate coefficient the sign of the inconsistency is related to the underlying parameters of the model. We also show that sign reversal may occur in the estimation of the cross rate effect; this is not however possible in estimation of the own rate effect. Copyright 1989 by Blackwell Publishers Ltd and The Victoria University of Manchester
References: Add references at CitEc
Citations View citations in EconPapers (3) Track citations by RSS feed
There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
Persistent link: http://EconPapers.repec.org/RePEc:bla:manch2:v:57:y:1989:i:4:p:357-69
Access Statistics for this article
More articles in The Manchester School of Economic & Social Studies from University of Manchester Contact information at EDIRC.
Series data maintained by Wiley-Blackwell Digital Licensing ().