This paper analyses the performance of forecasts of real economic activity based on the Japanese official business indices in a real-time framework. As in other countries, preliminary numbers of the business indices are first announced, then they are revised. These revisions are often substantial, so that the business indices that are available on a real-time basis often differ from their revised form. This paper explores how this difference can affect forecasts. Results indicate that real-time forecasts based on the diffusion leading index are not significantly worse than forecasts based on the final revised form. Also, the real-time forecasts using the composite leading index are often comparable to those from final revised forms. However, real-time forecasts from the diffusion coincident index are significantly worse than forecasts that use the final revised form.

View full abstract

In this paper, we investigate volatility in Japanese stock returns, using the state-space model. The daily data of Nikkei 225 stock average from January 4, 1985 to June 10, 2004 are utilized and the stochastic volatility model is assumed for the noise component. We examine whether there are asymmetry, holiday and day-of-the-week effects in volatility. Moreover, we see whether U.S. stock price change influences the volatility in Japanese stock price, which is called U.S. stock price change effect in this paper (note that this is the asymmetry effect caused by U.S. stock market). It is also examined whether we have volatility transmission from U.S. to Japan. As a result, we empirically find that the asymmetry, holiday, U.S. stock price volatility transmission and Tuesday effects strongly influence the volatility in Japanese stock returns. Moreover, it is shown that both volatility and level in Japanese stock returns depend on U.S. stock returns.

View full abstract

This paper is intended as an investigation of estimating functionals of a lifetime distribution F under right censorship. Functionals given by ∫ φdF, where φ’s are known F-integrable functions, are considered. The nonparametric maximum likelihood estimator of F is given by the Kaplan-Meier (KM) estimator F_n, where n is sample size. A natural estimator of ∫ φdF is a KM integral, ∫ φdF_n. However, it is known that KM integrals have serious biases for unbounded φ’s. A representation of the KM integral in terms of the KM estimator of a censoring distribution is obtained. The representation may be useful not only to calculate the KM integral but also to characterize the KM integral from a point view of the censoring distribution and the biasedness. A class of unbiased estimators under the condition that the censoring distribution is known is considered, and the estimators are compared.

View full abstract

In this paper we consider the problem of testing for a parameter change in regression models with ARCH errors based on the residual cusum test. It is shown that the limiting distribution of the residual cusum test statistic is the sup of a Brownian bridge. Through a simulation study, it is demonstrated that the proposed test circumvents the drawbacks of Kim et al.’s (2000) cusum test. For illustration, we apply the residual cusum test to the return of yen/dollar exchange rate data.

View full abstract

From the decision-theoretic viewpoint, using a weighted loss we compare the risks of testing procedures in the location and scale parameter cases. We also get numerically the minimax solution of Bayes testing procedures w.r.t. a parameter of the prior distribution, under the weighted loss.

View full abstract

We consider the problem of constructing a nonlinear discriminant procedure, using a regularized local likelihood method. The local likelihood method is effective for analyzing data with complex structure and applicable to discriminant analysis within the framework of logistic regression. The stability of the local likelihood estimators, however, is not guaranteed in the case that the structure of the system is quite complex. Instability of the local likelihood estimators may affect the construction of the discriminant boundary region. In order to overcome this difficulty, we propose the regularized local likelihood method which unites local likelihood and regularization.
A crucial issue in constructing nonlinear discriminant models is a choice of smoothing parameter and regularization parameter. In order to evaluate constructed models estimated by the regularized local likelihood method, we derive a model selection criterion from an information-theoretic point of view. We apply our discriminant procedure to real data. The results show that our technique performs well in the sense of minimizing the test error, and that clear improvements are achieved by employing the regularization.

View full abstract

This paper is concerned with estimation of the restricted parameters in location and/or scale families from a decision-theoretic point of view. A simple method is provided to show the minimaxity of the best equivariant and unrestricted estimators. This is based on a modification of the known method of Girshick and Savage (1951) and can be applied to more complicated cases of restriction in the location-scale family. Classes of minimax estimators are also constructed by using the IERD method of Kubokawa (1994a, b): Especially, the paper succeeds in constructing such a class for estimating a restricted mean in a normal distribution with an unknown variance.

View full abstract