Linear model identification by least squares method as applied to ship motion

2012 ◽  
Vol 3 (2) ◽  
pp. 100-103
Author(s):  
M. V. Sotnikova
2020 ◽  
pp. 636-645
Author(s):  
Hussain Karim Nashoor ◽  
Ebtisam Karim Abdulah

Examination of skewness makes academics more aware of the importance of accurate statistical analysis. Undoubtedly, most phenomena contain a certain percentage of skewness which resulted to the appearance of what is -called "asymmetry" and, consequently, the importance of the skew normal family . The epsilon skew normal distribution ESN (μ, σ, ε) is one of the probability distributions which provide a more flexible model because the skewness parameter provides the possibility to fluctuate from normal to skewed distribution. Theoretically, the estimation of linear regression model parameters, with an average error value that is not zero, is considered a major challenge due to having difficulties, as no explicit formula to calculate these estimates can be obtained. Practically, values for these estimates can be obtained only by referring to numerical methods. This research paper is dedicated to estimate parameters of the Epsilon Skew Normal General Linear Model (ESNGLM) using an adaptive least squares method, as along with the employment of the ordinary least squares method for estimating parameters of the General Linear Model (GLM). In addition, the coefficient of determination was used as a criterion to compare the models’ preference. These methods were applied to real data represented by dollar exchange rates. The Matlab software was applied in this work and the results showed that the ESNGLM represents a satisfactory model. 


Author(s):  
V. A. Galanina ◽  
◽  
L. A. Reshetov ◽  
M. V. Sokolovskay ◽  
A. E. Farafonova ◽  
...  

The paper investigates the effect of distorsions of the linear model matrix on the statistical characteristics of the least squares estimates.


2021 ◽  
Vol 906 (1) ◽  
pp. 012056
Author(s):  
Maria Mrówczyńska ◽  
Jacek Sztubecki ◽  
Zofia Ziçba ◽  
Izabela Wilczyńska

Abstract The geodetic monitoring of engineering structures, their displacements, and deformations, carried out permanently or periodically, allows obtaining information on the technical condition of facilities. The achieved information enables determining the necessary changes in using objects and minimizing future errors in the similar object’s design. The measurement results are subject to geometric interpretation based on the determined displacement parameters of the object’s shape and the approximation of the vector displacement field. Due to the influence of random factors characterized by a change in time and varying intensity, the deformation measurements performed during the operation of the facilities are of great importance for the safety of structures and engineering structures. In actual tasks of determining the object’s deformation and building a geometric model of displacements, the dominant method is the differential method, the advantage of eliminating systematic errors in measurement results while maintaining the geometric structure of the measurement and control network. The displacement’s geometric model, built based on measurements and calculations, can build a dynamic model of a building object, additionally considering such causes of deformation as, for example, own and usable weight, wind pressure, changes in ambient temperature, or ground vibrations. The article proposes approaches using the free alignment of linear and angular observations made in a geodetic network to determine horizontal displacements of an engineering object. This method may be necessary to study displacements of various parts of the object, thus analyzing its deformation. Free alignment allows for an optimal fit of the equalized network into the approximate network by imposing additional conditions (compared to the classic least squares method) on the vector of estimates of increments to approximate coordinates and the value of the covariance matrix. As an example of applying the proposed approach, the actual data received from the geodetic monitoring of the building structure was used. The structure was a road viaduct located along Wojska Polskiego Street in Bydgoszcz. The object of measurements and analyses was represented by finite sets of fixed points, subject to periodic observations over two years. The authors tested the effectiveness of the proposed algorithm and compared the obtained results with the values of horizontal displacements, which were calculated based on the classic study of geodetic monitoring results using the least-squares method. The accuracy analysis of the obtained values of the geodetic network horizontal displacements using free alignment and the least-squares method was also performed. The results indicate the possibility of using the presented approach to identify the geometric model of horizontal displacements without losing the accuracy of their determination.


Author(s):  
Gidon Eshel

This chapter focuses on linear regression, the process of identifying the unique model that best explains a set of observed data among a specified class of general models. Regression thus occupies a uniquely important position at the very interface of modeling and data analysis. Regression arises very often, in various guises, in handling and analyzing data. Since it is one of the most basic, useful, and frequently employed data analysis tools, and since some understanding of regression is needed in later sections, regression will be discussed in some detail. Topics covered include setting up the problem; the linear system Ax = b, least squares, special problems giving rise to linear systems, statistical issues in regression analysis, and multidimensional regression and linear model identification.


2010 ◽  
Vol 143-144 ◽  
pp. 1328-1331
Author(s):  
Hai Jun Chen ◽  
Xiao Ling Liu ◽  
Ling Hui Liu

The least squares method is very sensitive to outliers, one of the simple alternative is the least absolute deviation, i.e. L1 regression, which is less sensitive to outliers, so which is more suitable the small sample and much noise situation. In this paper, the L1 problem of linear model is discussed, the previous work is reviewed systematically, different algorithms is compared, it is proved that the dual forms of different algorithms are the same.


Sign in / Sign up

Export Citation Format

Share Document