Volume 20, Issue 2

This paper proposes a cumulated sum (CUSUM) test for the null hypothesis of quantile cointegration. A fully modified quantile estimator is adopted for serial correlation and endogeneity corrections. The CUSUM statistic is composed of the partial sums of the residuals from the fully modified quantile regression. Under the null, the test statistic converges to a functional of Brownian motions. In the application to US interest rates of different maturities, evidence in favor of the expectations hypothesis for the term structure is found in the central part of the distributions of the Treasury bill rate and financial commercial paper rate, but in the tails of the constant maturity rate distribution.

This paper builds a novel multi-criteria, non-parametric classification framework in order to improve the accuracy of pricing European options. The proposed approach is based on classifying financial options according to their implied volatility, time to maturity and moneyness. Using a recent data set for the daily S&P 500 index call options, the multi-criteria modular neural network model demonstrates its superior out-of-sample pricing performance relative to competing parametric and non-parametric models. By observing the model’s pricing errors across various option types, the analysis provides additional insights into pricing biases and stresses the importance of selecting appropriate classification criteria.

Detrending within structural vector autoregressions (SVAR) is directly linked to the shock identification. We investigate the consequences of trend misspecification in an SVAR using both standard real business cycle models and bi-variate SVARs as data generating processes. Our bias decomposition reveals biases arising directly from trend misspecification are not trivial when compared to other widely studied misspecifications. Misspecifying the trend also distorts impulse response functions of even the correctly detrended variable within the SVAR system. Pretesting for unit roots mitigates trend misspecification to some extent. We also find that while practitioners can specify high lag order VARs to mitigate trend misspecification, relying on common information criterion such as the Akaike information criterion (AIC) or Bayesian information criterion (BIC) may choose a lag order that is too low.

Standard time varying parameter (TVP) models usually assume independent stochastic processes. In this paper, I show that the number of underlying sources of parameters’ time variation is likely to be small, and provide empirical evidence for factor structure amongst TVPs of popular macroeconomic models. In order to test for the presence of low dimension sources of time variation in parameters and estimate their magnitudes, I develop the factor time varying parameter (Factor-TVP) framework and apply it to [Primiceri, G.E. (2005), “Time Varying Structural Vector Autoregressions and Monetary Policy,” The Review of Economic Studies , 72, 821–852] monetary TVP-VAR model. I find that one factor explains most of the variability in VAR coefficients, while the stochastic volatility parameters vary independently. The inclusion of post-“Great Recession” data causes an important change within VAR coefficients and the procedure suggests two factors. The roots of variability in the VAR parameters are likely to have derived from the financial markets and the real sector. The TVP factors have predictive power for a large number of output, investment, and employment series, as well as for the term structure of interest rates.

(Bakshi, G., and Z. Chen. 1997. “Equilibrium Valuation of Foreign Exchange Claims.” Journal of Finance 52: 799–826) studied equilibrium valuation for foreign exchange claims in the setting of the two-country Lucas-type economy. In Bakshi and Chen (1997), they assumed the money supplies follow two-factor stochastic volatility processes. Based on their model, we add two independent Poisson-type jumps, respectively into the process of money supply in each country. By solving a partial integro-differential equation (PIDE) for currency options, we get closed-form solutions of call currency option prices. Our model is a generalization of Bakshi and Chen (1997), and can contain a class of stochastic-volatility jump-diffusion (SVJD) models as special cases.

This paper revisits the statistical specification of near-multicollinearity in the logistic regression model. We argue that the ceteris paribus clause, which assumes that the maximum likelihood estimator of β remains constant as the correlation ( ρ ) between the regressors increases, invoked under the traditional account of near-multicollinearity is rather misleading. We derive the parameters of the logistic regression model and show that they are functions of ρ , indicating that the ceteris paribus clause is unattainable. Monte Carlo simulations confirm these findings and further show that: coefficient estimates and related statistics fluctuate in a non-symmetric, non-monotonic way as | ρ |→1; that the impact of near-multicollinearity is centered on the estimates of β ; and that the impact on substantive inferences does not necessarily follow what the traditional account implies.