BAYESIAN LINEAR PREDICTION IN FINITE POPULATIONS

被引：6

作者：

BOLFARINE, H ^{[1
]}

机构：

[1] UNIV SAO PAULO,INST MATEMAT & ESTAT,AGENCIA IGUATEMI,BR-01498 SAO PAULO,BRAZIL

来源：

ANNALS OF THE INSTITUTE OF STATISTICAL MATHEMATICS | 1990年 / 42卷 / 03期

关键词：

Bayes linear prediction; dynamic superpopulation model; mixed linear model; parameter dependent error variance;

D O I：

10.1007/BF00049300

中图分类号：

O21 [概率论与数理统计]; C8 [统计学];

学科分类号：

020208 ; 070103 ; 0714 ;

摘要：

In this paper, Bayesian linear prediction of the total of a finite population is considered in situations where the observation error variance is parameter dependent. Connections with least squares prediction (Royall (1976, J. Amer. Statist. Assoc., 71, 657-664)) in mixed linear models (Theil (1971, Principles of Econometrics, Wiley, New York)), are established. Extensions to the case of dynamic (state dependent) superpopulation models are also proposed. © 1990 The Institute of Statistical Mathematics.

引用

页码：435 / 444

页数：10

共 14 条

[1] MODEL-BASED ESTIMATION IN FINITE POPULATION-SAMPLING [J].

BELLHOUSE, DR .

AMERICAN STATISTICIAN, 1987, 41 (04) :260-262

[2]

BINDER DA, 1988, HDB STATISTICS, V6

[3]

BLIGHT BJN, 1973, J ROY STAT SOC B, V35, P61

[4] POPULATION VARIANCE PREDICTION UNDER NORMAL DYNAMIC SUPERPOPULATION MODELS [J].

BOLFARINE, H .

STATISTICS & PROBABILITY LETTERS, 1989, 8 (01) :35-39

[5]

BOLFARINE H, 1987, SANKHYA SER B, V49, P23

[6] FINITE POPULATION PREDICTION UNDER DYNAMIC GENERALIZED LINEAR-MODELS [J].

BOLFARINE, H .

COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION, 1988, 17 (01) :187-207

[7]

FULLER WA, 1970, SIMPLE ESTIMATORS ME

[8]

RAO CR, 1973, LINEAR STATISTICAL I

[9] THE COORDINATE-FREE ESTIMATION IN FINITE POPULATION-SAMPLING [J].

RODRIGUES, J ;

ELIAN, SN .

STATISTICS & PROBABILITY LETTERS, 1989, 7 (04) :293-295

[10] LINEAR LEAST-SQUARES PREDICTION APPROACH TO 2-STAGE SAMPLING [J].

ROYALL, RM .

JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1976, 71 (355) :657-664

← 1 2 →