Seasonal Cointegration in Money Demand

Authors

  • Raimundo Soto
  • Matias Tapia

Abstract

Empirical estimates of the demand for money exhibit standard problems: model instability, parameter inconsistency with regard to theoretical priors, and poor forecasting capabilities (Goldfeld and Sichel, 1990). This study explores to what extent an inadequate treatment of seasonality is responsible for the disappointing results obtained in the Chilean case. The empirical approach is to test for the presence of unit roots at different frequencies of money balances and their main determinants (annual, semiannual, and quartely). Once seasonal integration is established, seasonal-cointegration error-correction models allow us to trace long-term relationships between these variables in a more satisfactory way than standard models. The estimated seasonal-cointegration demand for money —which excludes any ad-hoc variable— is stable and robust for 1977-1999 and its forecasting capability is superior to that of traditional models.

Downloads

Download data is not yet available.

Published

26-12-2000

How to Cite

Soto, R. ., & Tapia, M. . (2000). Seasonal Cointegration in Money Demand. ECONOMÍA CHILENA, 3(3), 57–71. Retrieved from http://xn--economachilena-5lb.cl/index.php/economiachilena/article/view/36

Issue

Section

Articles