John Huizinga

Two-Step Two-Stage Least Squares Estimation in Models with Rational Expectations

This paper introduces a limited-information two-step estimator for models with rational expectations and serially correlated disturbances. The estimator greatly extends the area of applicability of McCallums (1976) instrumental variables approach to rational expectations models. Section I reviews McCallum%s method and discusses in detail the problems surrounding its use in many empirical c/ntexts. Section II presents the two-step two-stage least squares estimator (2S2S1) and demonstrates its efficiency relative to that of McCallum (1979). Section III provides a comparison nf several estim!tors for a two equation macroeconomic model with rational expectations due to Taylor (1979).

Monetary Policy Regime Shifts and the Unusual Behavior of Real Interest Rates

A striking phenomenon of the early 1980s is the climb in real interest rates to levels unprecedented in the post-World War II period. In order to understand this phenomenon, this paper investigates the nature and timing of shifts in the real rate process to determine if the recent unusual behavior of real rates is associated with monetary policy regime changes. We find that not only are there significant shifts in the stochastic process of real interest rates in October 1979 and October 1982 when the Federal Reserve alters its behavior, but these dates are also found to be the most likely breakpoints in the real rate process. When we analyze another monetary policy regime change with many similarities to that of October 1979, the sharp rises in the discount rate in 1920, we also reach a similar conclusion; there is a striking correspondence between the monetary policy regime change and the shift in the real rate process. Other studies have examined competing explanations for the recent unusual behavior of real interest rates -- e.g.budget deficits or favorable changes in business taxation. Although these competing explanations have met with mixed success, our evidence lends substantial support to the view that monetary policy regime changes have been and continue to be an important source of shifts in the behavior of real interest rates.

Testing the Autocorrelation Structure of Disturbances in Ordinary Least Squares and Instrumental Variables Regressions

This paper derives the asymptotic distribution for a vector of sample autocorrelations of regression residuals from a quite general linear model. The asymptotic distribution forms the basis for a test of the null hypothesis that the regression error follows a moving average of order q [greaterthan or equal] 0 against the general alternative that autocorrelations of the regression error are non-zero at lags greater than q. By allowing for endogenous, predetermined and/or exogenous regressors, for estimation by either ordinary least squares or a number of instrumental variables techniques, for the case q>0, and for a conditionally heteroscedastic error term, the test described here is applicable in a variety of situations where such popular tests as the Box-Pierce (1970) test, Durbins (1970) h test, and Godfreys (1978b) Lagrange multiplier test are net applicable. The finite sample properties of the test are examined in Monte Carlo simulations where, with a sample sizes of 50 and 100 observations, the test appears to be quite reliable.

The Predictability of Real Exchange Rate Changes in the Short and Long Run

Nominal exchange rates do not move to offset differences in inflation rates on a month to month, quarter to quarter, or even year to year basis, resulting in sizable real exchange rate changes. Are these changes predictable? We address this question in three ways. First, we describe a variety of tests of predictability and explain how the different tests are related. Next, we implement the tests for the U.S. dollar relative to four currencies and find statistically significant evidence that real exchange rate changes are predictable. Finally, we examine whether the predictability is of an economically interesting magnitude.

Investigating the correlation of unobserved expectations: Expected returns in equity and foreign exchange markets and other examples

Abstract Many economic models yield the prediction that the unobservable conditional expectations of two series are perfectly correlated. In this paper, we propose an informative method for investigating this prediction. The method involves examining the sample correlation coefficient for the fitted values from unrestricted ordinary least squares regressions, and the estimated standard error and confidence interval of this correlation coefficient. The method is designed to supplement existing statistical tests, which are often uninformative about the exact nature in which the data agree or disagree with the prediction of perfect correlation. We also apply our method to three distinct models and data sets.

The signalling role of base and money announcements and their effects on interest rates

Abstract This paper demonstrates that unexpected changes in the announced monetary base have an impact on interest rates above and beyond the impact of unexpected changes in the announced money supply. In addition, both money supply and monetary base announcements are shown to have a significant signalling role for subsequent changes in monetary aggregates. However, in contrast to several leading hypotheses, it appears that the observed link between monetary announcements and interest rates is not attributable to the signals that announcements provide about the subsequent behavior of money and the base.

The impact of monetary announcements on forward interest rates: Movements in term premia or expected future rates?

Abstract Evidence is presented on how the response of forward interest rates to money supply and monetary base announcements is decomposed into movements in term premia and expected future interest rates. A significant movement of each component is found for at least one sample period.