日本統計学会誌

ESTIMATION OF THE AUTOCORRELATION COEFFICIENTS FOR A STATIONARY GAUSSIAN PROCESS BY RANDOM CLIPPING, II

Minoru Tanaka

1986 年 16 巻 2 号 p. 115-122
発行日: 1986年
公開日: 2009/01/22

DOIhttps://doi.org/10.11329/jjss1970.16.115

ジャーナルフリー

抄録を表示する抄録を非表示にする

This paper deals with the problem of estimating the autocorrelation coefficients of a stationary Gaussian process with known mean and unknown variance. We treat a kind of simplified estimate of the autocorrelations which is composed by using random clipping and numerically discuss the optimum clipping level which gives the minimum variance of the estimate, and also the variance is compared with that of an usual estimate.

抄録全体を表示

PDF形式でダウンロード (272K)
ON THE PARAMETER ESTIMATION FOR AN EXPLOSIVE PROCESS

Norio Watanabe

1986 年 16 巻 2 号 p. 123-131
発行日: 1986年
公開日: 2009/01/22

DOIhttps://doi.org/10.11329/jjss1970.16.123

ジャーナルフリー

抄録を表示する抄録を非表示にする

Problem of parameter estimation is considered for an explosive process which has a state space representation. We show strong consistency of least squares estimates of parameters for the case when the process is purely explosive, that is, all eigenvalues of the transition matrix lie outside the unit circle.

抄録全体を表示

PDF形式でダウンロード (321K)
AN APPLICAION OF A MIXTURE METHOD TO A CLASSIFICATION

Jogi Henna

1986 年 16 巻 2 号 p. 133-143
発行日: 1986年
公開日: 2009/01/22

DOIhttps://doi.org/10.11329/jjss1970.16.133

ジャーナルフリー

抄録を表示する抄録を非表示にする

A classification procedure is constructed by applying a mixture method based on a previously obtained observation from a mixed distribution when the number of constituents of the mixed distribution is finite but unknown. Next the convergence of the risk of classification by the procedure is investigated. Also some simulation results to estimate the number of component distributions are given. Furthermore a certain property of the procedure is investigated.

抄録全体を表示

PDF形式でダウンロード (450K)
SOME PROPERTIES OF THE LEAST SQUARES ESTIMATOR OF THE PARAMETERS OF THE HIDDEN PERIODICTY MODEL

Daniel W. U. Ebong

1986 年 16 巻 2 号 p. 145-152
発行日: 1986年
公開日: 2009/01/22

DOIhttps://doi.org/10.11329/jjss1970.16.145

ジャーナルフリー

抄録を表示する抄録を非表示にする

A stochastic process consisting of k>1 harmonic components plus stationary errors is considered under two models, models I and II for uni- and bi- directional data respectively. The asymptotic joint distribution of the frequencies and other parameters of the models are proved under both models as a direct consequence of the basic consistency of the frequencies as opposed to the proof given in Walker [6] for the approximate least squares estimator of the parameters of model I. Also the problems encountered by Walker [6] Section 5 when dealing with k>1 frequencies are overcome.

抄録全体を表示

PDF形式でダウンロード (351K)
A POOLING PROCEDURE FOR THE SCALE PROBLEM IN TWO LARGE SAMPLES

Koichi Inada, Itsuro Kakiuchi

1986 年 16 巻 2 号 p. 153-163
発行日: 1986年
公開日: 2009/01/22

DOIhttps://doi.org/10.11329/jjss1970.16.153

ジャーナルフリー

抄録を表示する抄録を非表示にする

A pooling procedure is proposed in two large samples for the scale problem from the point of view of statistical data analysis by applying the criteria of the heterogeneity and the homogeneity of two samples.

抄録全体を表示

PDF形式でダウンロード (420K)
AICS IN LOG LINEAR MODEL FOR CONTINGENCY TABLES WITH POISSON AND MULTINOMIAL DESIGNS

Sinji Tsuruta, Yoshiko Nogami

1986 年 16 巻 2 号 p. 165-172
発行日: 1986年
公開日: 2009/01/22

DOIhttps://doi.org/10.11329/jjss1970.16.165

ジャーナルフリー

PDF形式でダウンロード (269K)
COMPARING SOME MODIFIED MAXIMUM LIKELIHOOD ESTIMATORS OF A SLOPE COEFFICIENT IN A LINEAR FUNCTIONAL RELATIONSHIP

Naoto Kunitomo

1986 年 16 巻 2 号 p. 173-185
発行日: 1986年
公開日: 2009/01/22

DOIhttps://doi.org/10.11329/jjss1970.16.173

ジャーナルフリー

抄録を表示する抄録を非表示にする

We made a systematic comparison of modifications of the maximum likelihood (ML) estimator of a slope coefficient in a linear functional relationship model without replication. We investigate the asymptotic properties of estimators of a slope coefficient and its angle when the sample size and the spread of incidental parameters increase. The ML estimator and some modified estimators are dominated by an almost mean unbiased estimator in terms of the asymptotic mean squared error and the concentration of probability around the true coefficient parameter in this asymptotic theory.

抄録全体を表示

PDF形式でダウンロード (597K)
A NEW METHOD OF APPLYING AN EXTENDED MARGINAL HOMOGENEITY MODEL FOR SQUARE CONTINGENCY TABLES WITH ORDERED CATEGORIES

Sadao Tomizawa

1986 年 16 巻 2 号 p. 187-190
発行日: 1986年
公開日: 2009/01/22

DOIhttps://doi.org/10.11329/jjss1970.16.187

ジャーナルフリー

抄録を表示する抄録を非表示にする

The purpose of this note is to show an example for square contingency tables with ordered categories analysed using a new method of applying Tomizawa's [5, 6] extended marginal homogeneity model. A possible explanation which is derived from fitting that model is first obtained using this new method.

抄録全体を表示

PDF形式でダウンロード (184K)
SOME MODIFICATIONS OF EFRON-MORRIS ESTIMATOR AND THEIR MINIMAXITY

Nobuo Shinozaki

1986 年 16 巻 2 号 p. 191-201
発行日: 1986年
公開日: 2009/01/22

DOIhttps://doi.org/10.11329/jjss1970.16.191

ジャーナルフリー

抄録を表示する抄録を非表示にする

Stein estimator for p_??_3 normal means is known to dominate the usual estimator if the loss is quadratic. Efron and Morris [6] proposed an alternative to Stein estimator to limit the maximum component risk. We derive an unbiased estimator of the risk for a class of estimators and based on this we mainly discuss minimaxity of the estimators including the Efron-Morris estimator and its modifications. A weak admissibility of the estimators in the sense of component risk unbiased estimator is also given.

抄録全体を表示

PDF形式でダウンロード (445K)
統計教育研究の体制整備について

塩谷實

1986 年 16 巻 2 号 p. 203-217
発行日: 1986年
公開日: 2009/01/22

DOIhttps://doi.org/10.11329/jjss1970.16.203

ジャーナルフリー

PDF形式でダウンロード (1031K)
書評

Katsuto Tanaka

1986 年 16 巻 2 号 p. 219
発行日: 1986年
公開日: 2009/01/22

DOIhttps://doi.org/10.11329/jjss1970.16.219

ジャーナルフリー

PDF形式でダウンロード (76K)
日本統計学会第54回大会記録

1986 年 16 巻 2 号 p. 221-235
発行日: 1986年
公開日: 2009/01/22

DOIhttps://doi.org/10.11329/jjss1970.16.221

ジャーナルフリー

PDF形式でダウンロード (1052K)

J-STAGEへの登録はこちら（無料）