Analysing money demand relation for OECD countries using common factors

ABSTRACT

This article investigates the existence of a long-run money demand relation for a panel data consisting of 13 OECD countries. The analysis is based on the most recent data. The existence of a long-run money demand relation is tested with two new meta-analytic panel cointegrating rank tests which are robust to cross-sectional dependence. Cross-sectional dependency in the data generating process is modelled by unobserved common factors. The observed data are decomposed into idiosyncratic and common components, and these two components are analysed separately to find out the driving forces of the long-run stationary relationship. The evidence shows that the long-run money demand relation is driven by the cross-unit cointegration. Finally, the long-run relation is estimated by taking the common factors into account.

KEYWORDS:

• Panel cointegration
• money-demand
• common factors
• global stochastic trends
• cross-sectional dependence

JEL CLASSIFICATION:

• C33
• E41

Disclosure statement

No potential conflict of interest was reported by the author.

Supplemental data

Supplemental data for this article can be accessed here.

Notes

¹ Since broad money (M3) data are not available, for Japan, South Korea and Switzerland narrow money (M1) level is used instead. Although data on M3 are available, due to the short span of the long-term interest rates, Chile, Czech Republic, Hungary, Mexico, Poland and Turkey, had to be discarded from the analysis.

² Data for GDP deflator are not available for South Korea and prior to 1997 for Iceland. Therefore, for South Korea and Iceland the consumer price index for all items is used to compute the variables in real terms.

³ The scaled CD${\hspace{0.17em}}_{lm}$ statistic is computed by

$\mathrm{S}\mathrm{c}\mathrm{a}\mathrm{l}\mathrm{e}\mathrm{d}C{D}_{lm}=\sqrt{\frac{1}{N(N-1)}}\sum _{i=1}^{N-1}\sum _{j=i+1}^N(T{\hat{\rho }}_{ij}^2-1)\sim N(0,1),$

and the CD statistic of Pesaran (2015) is computed as

$CD=\sqrt{\frac{2T}{N(N-1)}}\sum _{i=1}^{N-1}\sum _{j=i+1}^N{\hat{\rho }}_{ij}\sim N(0,1),$

where ${\hat{\rho }}_{ij}$ being the pairwise correlation coefficient between the residuals of ith and jth units.

⁴ For further assumptions on the factors and the loadings, please refer to Örsal and Arsova (2017).

Additional information

Funding

This work was supported by the Deutsche Forschungsgemeinschaft [KA-3145/1-2].