Non‐linearity and exchange rates

Abstract

The conditional heteroscedastic models (CHM) are commonly used to describe the dynamics of nominal exchange rates. However, some investigations have already pointed out that the CHMs are not able to fully explain all non-linearities exhibited by the exchange rate series. This paper analyses the performance of univariate CHMs in modelling the nonlinearities of nominal exchange rate series vis-aÁ-vis the US dollar. Twelve currencies are examined on a weekly basis: The Belgian, Swiss and French francs; the Canadian dollar; the German mark; the Danish and Norwegian kroners; the British and Irish pounds; the Italian lira; the Japanese yen and the Dutch guilder. The CHMs captured in a satisfactory way the volatility clustering of the series and show volatility peaks in historically nervous periods of the international market. Moreover, the results of the BDS tests for whiteness applied to the standardized residuals show the good speci®ca-tion of the models. # 1998 John Wiley & Sons, Ltd.KEY WORDS conditional heteroscedastic models; BDS test; exchange ratesIn the absence of structural models, the conditional heteroscedastic models (CHMs) introduced by Engle (1982) are natural candidates for the econometric analysis of nominal exchange rates since they are able to capture properties such as volatility clustering and leptokurtosis. There are numerous investigations of exchange rates based on CHMs, generally using a GARCH (Generalized AutoRegressive Conditional HeteroscedasticÐBollerslev, 1986) speci®cation. Engle, Ito and Lin (1990) tried to identify the source of volatility clustering by analysing the diusion of intermarket information. The`meteor shower' hypothesis was shown to be more consistent than the`heat wave' assumption with the actual diusion process of information, since there was more evidence of intra-daily volatility spill-overs among markets than idiosyncratic volatility shocks. Similar results were also found by Baillie, Bollerslev and Redfearn (1993) when examining the US market of foreign exchange rate in the 1920s. proposed a seasonal GARCH model to describe intra-day exchange rates. They could not reject both`meteor shower' and`heat wave' hypotheses, such that both common and idiosyncratic volatility shocks may exist among dierent markets.Bollerslev (1990) estimated a multivariate GARCH for some European currencies aiming to evaluate the impact of the European Monetary System (EMS) on the behaviour of exchange * Correspondence to:

Why Do Emerging Stock Markets Experience More Persistent Price Deviations From a Random Walk Over Time? A Country-Level Analysis

“…The alternative hypothesis is that the process has some nonzero bicorrelations, hence implying nonlinearity in the conditional mean. In extant empirical literature, the third-order moment test has been widely adopted to distinguish the source of nonlinearity [see, for example, Fujihara and Mougoué (1997); Fernandes (1998);Yadav et al (1999); Saadi et al (2006)]. 7.…”

“…For comparison with previous studies, Table 1 also presents the degree of country-level market efficiency reported by Morck et al (2000), Jin and Myers (2006) and Fernandes andFerreira (2008, 2009). 11 The Spearman rank correlation results in Panel A show that our efficiency measure correlates weakly with the market model R 2 statistic.…”

“…12 This paper further explores whether cross-country variation in the degree of market efficiency can be traced to historically determined differences in legal tradition. This is motivated by the growing empirical evidence that highlights the ability of legal systems to account for cross-country differences in (1) the level of financial intermediary and stock market development [Beck et al (2001)]; (2) the ownership of banks by government [La Porta et al (2002)]; (3) the extent Notes: ROLLH denotes the proportion of significant rolling H statistics; MYY refers to Morck et al (2000); JM1 is the equal-weighted R 2 , whereas JM2 is the variance-weighted R 2 from Jin and Myers (2006); FF1 and FF2 stand for the market model R 2 s computed from Fernandes andFerreira (2008, 2009), respectively. Two-tailed p-values are presented in parentheses.…”

“…11. Fernandes andFerreira (2008, 2009) compute the relative firm-specific stock return variation, which is precisely one minus the market model R 2 . For consistency, we derive the market model R 2 from their reported median relative firm-specific stock return variation for each country.…”

Continuous ant colony optimization algorithms in a support vector regression based financial forecasting model

“…Otherwise, conduct the pheromone updating process represented as Eqs. (9) and (10) to renew the reinforcement of pheromone. Then, go back to Step 5. Notice that, in any iteration, while information exchange (shorter path) condition is attained, the appropriate solution is determined, and for those three parameters, new search space is then re-discretized.…”