Taylor rule deviations and out-of-sample exchange rate predictability

Abstract

The Taylor rule has become the dominant model for academic evaluation of out-of-sample exchange rate predictability. Two versions of the Taylor rule model are the Taylor rule fundamentals model, where the variables that enter the Taylor rule are used to forecast exchange rate changes, and the Taylor rule differentials model, where a Taylor rule with postulated coefficients is used in the forecasting regression. We use data from 1973 to 2014 to evaluate short-run out-ofsample predictability for eight exchange rates vis-à-vis the U.S. dollar, and find strong evidence in favor of the Taylor rule fundamentals model alternative against the random walk null. The evidence of predictability is weaker with the Taylor rule differentials model, and still weaker with the traditional interest rate differential, purchasing power parity, and monetary models. The evidence of predictability for the fundamentals model is not related to deviations from the original Taylor rule for the U.S., but is related to deviations from a modified Taylor rule for the U.S. with a higher coefficient on the output gap. The evidence of predictability is also unrelated to deviations from Taylor rules for the foreign countries and adherence to the Taylor principle for the U.S. A B S T R A C T Keywords:Exchange rates Out-of-sample exchange rate predictability Taylor rulesThe Taylor rule has become the dominant model for academic evaluation of out-of-sample exchange rate predictability. Two versions of the Taylor rule model are the Taylor rule fundamentals model, where the variables that enter the Taylor rule are used to forecast exchange rate changes, and the Taylor rule differentials model, where a Taylor rule with postulated coefficients is used in the forecasting regression. We use data from 1973 to 2014 to evaluate short-run out-of-sample predictability for eight exchange rates vis-à-vis the U.S. dollar, and find strong evidence in favor of the Taylor rule fundamentals model alternative against the random walk null. The evidence of predictability is weaker with the Taylor rule differentials model, and still weaker with the traditional interest rate differential, purchasing power parity, and monetary models. The evidence of predictability for the fundamentals model is not related to deviations from the original Taylor rule for the U.S., but is related to deviations from a modified Taylor rule for the U.S. with a higher coefficient on the output gap.

Application of Taylor Rule Fundamentals in Forecasting Exchange Rates

“…They incorporated the financial crisis into their work and found that the Taylor rule fundamentals have the power to predict the exchange rate. Ince et al (2016) extended the work by Molodtsova and Papell (2009) and demonstrated short-run out-of-sample predictability of the exchange rate with the two versions of the Taylor rule model for eight exchange rates vis-à-vis the U.S. dollar. Their research found strong evidence of exchange rate predictability with the Taylor rule fundamental model as compared to the Taylor rule differential and much stronger proof than the traditional exchange rate predictors.…”

“…Molodtsova and Papell (2012) examined the USD/EUR exchange rate during the financial crisis and found that the Taylor rule fundamental could still predict the exchange. Ince et al (2016) also proved the predictability of the Taylor rule fundamentals during the financial crisis and the great recession for eight countries.…”

“…However, the Taylor rule fundamentals do not put the estimated coefficients on the Taylor rule variables. Rather, the models only examine out-of-sample forecastability (Ince et al 2016). Therefore, further investigation into the connection between the Fed using the Taylor rule and the out-of-sample exchange rate forecastability is needed.…”

Quantum Monte Carlo simulations for estimating FOREX markets: a speculative attacks experience

“…The literature shows the different fit results after applying different statistical techniques and Monte Carlo algorithms for these Currency Market models. For example, models constructed with linear statistical techniques, such as Ordinary Least Squares, linear regression methods, and Factor models, have provided an adjustment of 0.93-1.84 standard deviation (Rossi, 2013;Park and Park, 2013;Byrnea et al, 2016;Ince et al, 2016;Serjam and Sakurai, 2018), but their adjustments are between 1.26-2.11 when constructed with small samples (Rossi, 2013;Jacob and Uusküla, 2019). On the other hand, other more advanced statistical models, especially non-linear models, such as Vector Autoregression, time-varying parameter models, and Error Correction models.…”

“…Byrne et al (2016) applied the Time-Varying Parameters method, for a sample of several OECD currencies per US dollar, obtaining an overall standard deviation of 0.72. Ince et al (2016) used ordinary least squares (OLS) to estimate theoretical models of the FOREX market for data on US dollar-Swiss franc and US dollar-Japanese Yen exchange rates. They got an overall standard deviation superior to 1.06 in their estimates.…”