Abstract
The Fisher effect specifies a positive, one-for-one relationship between the nominal interest rate and expected inflation. Most recent empirical studies on the Fisher equation, typically based on ordinary least squares and co-integration estimation, found that the equation did not fit various data sets well. However, recent empirical studies showed that this fit improves if the Fisher equation is treated as a non-linear equation. Using U.S. quarterly data, this paper examines whether the results of the previous studies on the Fisher equation arose as a direct consequence of specification errors. We use time-varying coefficient (TVC) estimation, a procedure that allows us to directly confront the unknown functional form problem, specification errors, and spurious relationships. We find strong support for the view that, under TVC estimation, the Fisher equation holds and is no longer a puzzle.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Notes
Fisher (1930) also argued that nominal interest movements lag behind movements in the inflation rate. He originated the distributed lag concept to measure inflation expectations.
Earlier studies, based strictly on OLS estimation and distributed lags to measure inflation expectations, also found that the Fisher relationship did not hold. See the studies contained in Gibson and Kaufman (1971).
The discussion below draws on Swamy et al. (2008).
That is, the number of determinants is itself time-varying.
These correlations are typically ignored in the analyses of state-space models. Thus, inexpressive conditions and restrictive functional forms are avoided in arriving at equations (5) and (6) so that Theorem 1 can easily hold; for further discussion and interpretation of the terms in (5) and (6), see Swamy and Tavlas (1995, 2001); Hondroyiannis et al. (2009) and Hall et al. (2008).
We use the term spurious in a more general sense than Granger and Newbold’s (1974), where it strictly applies to linear models with unit-root non-stationary error terms. Here we mean any correlation which is observed between two variables when the true direct effect is actually zero.
All the coefficient estimates from the TVC estimation reported are the time averages of the coefficient estimates.
References
Basmann RL (1988) Causality tests and observationally equivalent representations of econometric models. J Econom 39:69–104
Chang I, Hallahan C, Swamy PAVB (1992) Efficient computation of stochastic coefficient models. In: Amman HM, Belsley DA, Pau LF (eds) Computational economics and econometrics. Kluwer, London
Chang I, Swamy PAVB, Hallahan C, Tavlas GS (2000) A computational approach to finding causal economic laws. Comput Econ 16:105–136
Chow GC (1960) Tests of equality between sets of coefficients in two linear regressions. Econometrica 52:211–222
Christopoulos DK, Leon-Ledesma MA (2007) A long-run non-linear approach to the Fisher effect. J Money Credit Bank 39(2–3):543–559
Fisher I (1930) The theory of interest. Macmillan, New York
Gibson WE, Kaufman GG (eds) (1971) Monetary economics: readings on current issues. McGraw-Hill Book Company, New York
Granger CWJ, Newbold P (1974) Spurious regressions in econometrics. J Econom 2:111–20
Hall SG, Hondroyiannis G, Swamy PAVB, Tavlas GS (2008) The new Keynesian Phillips curve and lagged inflation: a case of spurious correlation? Southern Economic Journal, forthcoming.
Hondroyiannis G, Swamy PAVB, Tavlas GS (2009) The new Keynesian Phillips curve in a time-varying coefficient environment: some European evidence. Macroecon Dyn 12:149–166
Lanne M (2006) Nonlinear dynamics of interest rate and inflation. J Appl Econ 21:1157–1168
Maki D (2005) Asymmetric adjustment of the equilibrium relationship between nominal interest rate and inflation. Econ Bull 3:1–8
Million N (2004) Central banks interventions and the Fisher hypothesis: a threshold cointegration investigation. Econ Model 21:1051–64
Ng S, Perron P (2001) Lag length selection and the construction of unit root tests with good size and power. Econometrica 69:1519–1554
Pratt JW, Schlaifer R (1984) On the nature and discovery of structure. J Am Stat Assoc 79:9–22
Pratt JW, Schlaifer R (1988) On the interpretation and observation of laws. J Econom 39:23–52
Sun Y, Phillips PCB (2004) Understanding the Fisher equation. J Appl Econ 19:869–86
Swamy PAVB, Tavlas GS (1995) Random coefficient models: theory and applications. J Econ Surv 9:165–182
Swamy PAVB, Tavlas GS (2001) Random coefficient models. In: Baltagi BH (ed) A companion to theoretical econometrics. Blackwell, Malden
Swamy PAVB, Tavlas GS, Mehta JS (2007) Methods of distinguishing between spurious regressions and causality. J Stat Theory Appl 1:83–96
Swamy PAVB, Tavlas GS, Hall SG, Hondroyiannis G (2008) Estimation of parameters in the presence of model misspecification and measurement error. Mimeo.
Zellner A (1979) Causality and econometrics. In: Brunner K, Meltzer AH (eds) Three aspects of policy and policymaking. North-Holland, Amsterdam, pp 9–54
Zellner A (1988) Causality and causal laws in economics. J Econom 39:7–21
Author information
Authors and Affiliations
Corresponding author
Additional information
The views expressed are those of the authors and should not be interpreted as those of their respective institutions.
P. A. V. B. Swamy retired
Rights and permissions
About this article
Cite this article
Hall, S.G., Hondroyiannis, G., Swamy, P.A.V.B. et al. The Fisher Effect Puzzle: A Case of Non-Linear Relationship?. Open Econ Rev 21, 91–103 (2010). https://doi.org/10.1007/s11079-009-9157-1
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11079-009-9157-1