Simulation study of a linear relationship between two variables affected by errors

被引：3

作者：

Elfessi, A ^{[1
]}

Hoar, RH ^{[1
]}

机构：

[1] Univ Wisconsin, Dept Math, La Crosse, WI 54601 USA

来源：

JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION | 2001年 / 71卷 / 01期

关键词：

ordinary least squares; total least squares; slope; vertical distance; horizontal distance; weighted deviations;

D O I：

10.1080/00949650108812132

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

Suppose an experiment requires the fitting of a linear relationship Y = alpha + betaX to data, (x(i), y(i)) where X and Y were both measured subject to error. In this paper a variety of methods are used to estimate the value of the slope beta. Many popular methods are reformulated into a single class of optimization problems. Each method studied seeks to minimize a combination of the sum of the weighted deviations in the horizontal and vertical directions. The reformulation of each method is presented along with the results of a simulation study of the methods.

引用

页码：29 / 40

页数：12

共 50 条

[1] LINEAR RELATIONSHIPS BETWEEN VARIABLES AFFECTED BY ERRORS
CARLSON, FD
SOBEL, E
WATSON, GW
[J]. BIOMETRICS, 1966, 22 (02) : 252 - &
[2] On a symmetrized simulation extrapolation estimator in linear errors-in-variables models
Polzehl, J
Zwanzig, S
[J]. COMPUTATIONAL STATISTICS & DATA ANALYSIS, 2004, 47 (04) : 675 - 688
[3] Linear least squares fit when both variables are affected by equal uncorrelated errors
Petrolini, Alessandro
[J]. AMERICAN JOURNAL OF PHYSICS, 2014, 82 (12) : 1178 - 1185
[4] Exploring the relationship between temperature forecast errors and Earth system variables
Ruiz-Vasquez, Melissa
Sungmin, O.
Brenning, Alexander
Koster, Randal D.
Balsamo, Gianpaolo
Weber, Ulrich
Arduini, Gabriele
Bastos, Ana
Reichstein, Markus
Orth, Rene
[J]. EARTH SYSTEM DYNAMICS, 2022, 13 (04) : 1451 - 1471
[5] LINEAR ERRORS-IN-VARIABLES MODELS
DEISTLER, M
[J]. LECTURE NOTES IN CONTROL AND INFORMATION SCIENCES, 1986, 86 : 37 - 68
[6] IDENTIFICATION IN THE LINEAR ERRORS IN VARIABLES MODEL
KAPTEYN, A
WANSBEEK, T
[J]. ECONOMETRICA, 1983, 51 (06) : 1847 - 1849
[7] ERRORS IN VARIABLES IN LINEAR-SYSTEMS
LEAMER, EE
[J]. ECONOMETRICA, 1987, 55 (04) : 893 - 909
[8] IS RELATIONSHIP BETWEEN ACOUSTIC AND ARTICULATORY VARIABLES IN SPEECH INTRINSICALLY LINEAR
ATAL, BS
[J]. JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 1974, 55 (02): : 384 - 385
[9] THE IDENTIFIABILITY OF A LINEAR RELATIONSHIP BETWEEN VARIABLES WHICH ARE SUBJECT TO ERROR
REIERSOL, O
[J]. BIOMETRICS, 1949, 5 (01) : 88 - 89
[10] Comparison of LS techniques for the linear approximation of data affected by heteroschedastic errors in both variables with uncertainty estimation
Ichim, D
Ciarlini, P
Pavese, F
Premoli, A
Rastello, ML
[J]. ADVANCED MATHEMATICAL & COMPUTATIONAL TOOLS IN METROLOGY VI, 2004, 66 : 293 - 298

← 1 2 3 4 5 →