Kariya and Tsuda (1994) proposed the TDM (Time Dependent Markov) bond pricing model and showed that it is of great in-sample performance. In less than 0.5 yen in each month over 12 years, implying that the error rate is less than 0.5%. In addition, Kariya and Tsuda (1996) demonstrated the...

This paper extensively investigates the theory of estimating the regression coefficient matrix for the normal GNANOVA model. We explicitly construct estimators which improve the maximum likehood estimator under an invariant scalar loss function. These include the double shrinkage estimators and...

In this paper, first we make a maximal extension of the well known gauss-Markov Theorem (GMT) in its linear framework. In particular, the maximal class of distributions of error term for which teh GMT holds is derived.Second, we establish a nonlinear version of the maximal GMT and describe some...

In the GMANOVA model or equivalentry growth curve model, shrinkage effects on the MLE are considered under an invariant risk matrix. We first study the fundamental structure of the problem through which we decompose the estimation problem into some conditional problems and then demonstrate some...

This article proves that the stochastic process of returns decribed by S. Taylor's heteroscedastic nonlinear model converges in distribution to an iid normal process (normal white noise) as the number of the terms of temporal aggregetion increases.