Search results

1 – 10 of over 24000
Click here to view access options
Article
Publication date: 20 May 2020

Houzhe Zhang, Defeng Gu, Xiaojun Duan, Kai Shao and Chunbo Wei

The purpose of this paper is to focus on the performance of three typical nonlinear least-squares estimation algorithms in atmospheric density model calibration.

Abstract

Purpose

The purpose of this paper is to focus on the performance of three typical nonlinear least-squares estimation algorithms in atmospheric density model calibration.

Design/methodology/approach

The error of Jacchia-Roberts atmospheric density model is expressed as an objective function about temperature parameters. The estimation of parameter corrections is a typical nonlinear least-squares problem. Three algorithms for nonlinear least-squares problems, Gauss–Newton (G-N), damped Gauss–Newton (damped G-N) and Levenberg–Marquardt (L-M) algorithms, are adopted to estimate temperature parameter corrections of Jacchia-Roberts for model calibration.

Findings

The results show that G-N algorithm is not convergent at some sampling points. The main reason is the nonlinear relationship between Jacchia-Roberts and its temperature parameters. Damped G-N and L-M algorithms are both convergent at all sampling points. G-N, damped G-N and L-M algorithms reduce the root mean square error of Jacchia-Roberts from 20.4% to 9.3%, 9.4% and 9.4%, respectively. The average iterations of G-N, damped G-N and L-M algorithms are 3.0, 2.8 and 2.9, respectively.

Practical implications

This study is expected to provide a guidance for the selection of nonlinear least-squares estimation methods in atmospheric density model calibration.

Originality/value

The study analyses the performance of three typical nonlinear least-squares estimation methods in the calibration of atmospheric density model. The non-convergent phenomenon of G-N algorithm is discovered and explained. Damped G-N and L-M algorithms are more suitable for the nonlinear least-squares problems in model calibration than G-N algorithm and the first two algorithms have slightly fewer iterations.

Details

Aircraft Engineering and Aerospace Technology, vol. 92 no. 7
Type: Research Article
ISSN: 1748-8842

Keywords

Click here to view access options
Article
Publication date: 1 January 1986

ROGER N. CONWAY and RON C. MITTELHAMMER

In the last two decades there has been considerable progress made in the development of alternative estimation techniques to ordinary least squares (OLS) regression. The…

Abstract

In the last two decades there has been considerable progress made in the development of alternative estimation techniques to ordinary least squares (OLS) regression. The search for alternative estimators has no doubt been motivated by the observance of erratic OLS estimator behavior in cases where there are too few observations, multicollinearity problems, or simply “information‐poor” data sets. Imprecise and unreliable OLS coefficient estimates have been the result.

Details

Studies in Economics and Finance, vol. 10 no. 1
Type: Research Article
ISSN: 1086-7376

Click here to view access options
Book part
Publication date: 25 July 1997

Ehsan S. Soofi

Abstract

Details

Applying Maximum Entropy to Econometric Problems
Type: Book
ISBN: 978-0-76230-187-4

Click here to view access options
Article
Publication date: 9 November 2012

R. Farnoosh, P. Nabati and A. Hajirajabi

The main purpose of this paper is to estimate the resistance and inductor in the RL electrical circuit when these are unavailable or missing data that it is a concern in…

Abstract

Purpose

The main purpose of this paper is to estimate the resistance and inductor in the RL electrical circuit when these are unavailable or missing data that it is a concern in electrical engineering. The input voltage is assumed to be corrupted by the noise and the current is observed at discrete time points.

Design/methodology/approach

The authors propose a computationally efficient framework for parameters estimation using least square estimator and Bayesian Monte Carlo scheme.

Findings

The explicit formulas for least square estimator are derived and the strong consistency of resistance estimator is verified when inductor is a known parameter, then Bayesian estimation of parameters governed by using Markov chain Monte Carlo methods. The applicability of the results is demonstrated by using numerical examples. Several numerical results and figures are presented via Matlab and R programming to illustrate the performance of the estimators.

Practical implications

The paper can be used in various types of electrical engineering real time projects. The projects include electrical circuits, electrical machines theory and drives, especially when the parameters are uncertain that it is a worry in electrical engineering.

Originality/value

To the author's best knowledge, least square and Bayesian estimation of resistance and inductor have not been studied before. The proposed model is nonlinear with respect to inductor (L); therefore the present work has fundamental difference in comparison with the similar models.

Details

COMPEL - The international journal for computation and mathematics in electrical and electronic engineering, vol. 31 no. 6
Type: Research Article
ISSN: 0332-1649

Keywords

Click here to view access options
Article
Publication date: 1 March 1991

David Blake

The different types of estimators of rational expectations modelsare surveyed. A key feature is that the model′s solution has to be takeninto account when it is estimated…

Abstract

The different types of estimators of rational expectations models are surveyed. A key feature is that the model′s solution has to be taken into account when it is estimated. The two ways of doing this, the substitution and errors‐in‐variables methods, give rise to different estimators. In the former case, a generalised leastsquares or maximum‐likelihood type estimator generally gives consistent and efficient estimates. In the latter case, a generalised instrumental variable (GIV) type estimator is needed. Because the substitution method involves more complicated restrictions and because it resolves the solution indeterminacy in a more arbitary fashion, when there are forward‐looking expectations, the errors‐in‐variables solution with the GIV estimator is the recommended combination.

Details

Journal of Economic Studies, vol. 18 no. 3
Type: Research Article
ISSN: 0144-3585

Keywords

Click here to view access options
Article
Publication date: 8 April 2014

Dennis Olson and Taisier A. Zoubi

This study aims to examine the determinants of the allowance for loan losses (ALL) and loan loss provisions (LLP) for banks in the Middle East and North African (MENA…

Abstract

Purpose

This study aims to examine the determinants of the allowance for loan losses (ALL) and loan loss provisions (LLP) for banks in the Middle East and North African (MENA) region using both a two-stage approach and simultaneous equation system to address the potential problem of estimation bias introduced by estimating the ALL and LLP separately. The paper also tests three competing hypotheses: the earnings management hypothesis, the capital management hypothesis, and the signaling hypothesis.

Design/methodology/approach

The authors adopt a simultaneous equation and three-stage approaches to test whether MENA banks jointly determine LLP and ALL and the determinants of the two accounts. The sample consists of all available electronic data for 75 banks (451 bank-year observations) in nine MENA countries over the period 2000-2008.

Findings

Evidence suggests that the two accounts are jointly determined. The results support the earnings management hypothesis – meaning that MENA banks have engaged in year-to-year income smoothing. The authors also find that LLP and ALL provide signals about future earnings.

Research limitations/implications

The authors acknowledge that the LLP account is only one of many accounts on the income statement that could be used for signaling or to manage earnings, and that the ALL is one of several accounts that could be used for signaling, earnings or capital management. Future studies could examine other accruals for their role in managing earnings, signaling and capital.

Practical implications

The results indicate that bank managers use LLP and ALL accounts to manage earnings management, policy makers may want to limit the ability of banks to manipulate earnings.

Originality/value

Prior research on the loan loss accounting practices has been based on single equation models of the determinants of LLP and ALL. An issue that has not been adequately addressed in this literature is that ALL and LLP may be interrelated and jointly determined by banks. If the two accounts are not independent of each other, failure to include one when estimating the other may lead to an omitted variable problem, while including both in the same equation induces a potential simultaneity bias. The study is the first empirical work examining whether ALL and LLP are jointly determined by banks. By jointly estimating LLP and ALL, the study permits an assessment of the magnitude of the potential error from adopting ordinary least squares estimation of a single equation model.

Details

Journal of Islamic Accounting and Business Research, vol. 5 no. 1
Type: Research Article
ISSN: 1759-0817

Keywords

Click here to view access options
Book part
Publication date: 30 December 2004

James P. LeSage and R. Kelley Pace

For this discussion, assume there are n sample observations of the dependent variable y at unique locations. In spatial samples, often each observation is uniquely…

Abstract

For this discussion, assume there are n sample observations of the dependent variable y at unique locations. In spatial samples, often each observation is uniquely associated with a particular location or region, so that observations and regions are equivalent. Spatial dependence arises when an observation at one location, say y i is dependent on “neighboring” observations y j, y j∈ϒi. We use ϒi to denote the set of observations that are “neighboring” to observation i, where some metric is used to define the set of observations that are spatially connected to observation i. For general definitions of the sets ϒi,i=1,…,n, typically at least one observation exhibits simultaneous dependence, so that an observation y j, also depends on y i. That is, the set ϒj contains the observation y i, creating simultaneous dependence among observations. This situation constitutes a difference between time series analysis and spatial analysis. In time series, temporal dependence relations could be such that a “one-period-behind relation” exists, ruling out simultaneous dependence among observations. The time series one-observation-behind relation could arise if spatial observations were located along a line and the dependence of each observation were strictly on the observation located to the left. However, this is not in general true of spatial samples, requiring construction of estimation and inference methods that accommodate the more plausible case of simultaneous dependence among observations.

Details

Spatial and Spatiotemporal Econometrics
Type: Book
ISBN: 978-0-76231-148-4

Click here to view access options
Article
Publication date: 1 January 2010

James Mixon

Model estimation gives students insights beyond what they can gain from textbook presentations. This paper introduces a way to make doing this easier and more effective…

Downloads
1595

Abstract

Purpose

Model estimation gives students insights beyond what they can gain from textbook presentations. This paper introduces a way to make doing this easier and more effective. It introduces the program Gnu Regression, Econometrics and Time‐series Library (GRETL) which may be downloaded free of charge, and which students can place on their computers quickly and easily. Using GRETL to produce ordinary least squares (OLS) estimates is an easy, intuitive exercise. Therefore, instructors may assign such exercises without taking a large amount of time to introduce the computer and OLS estimation. GRETL, though designed to facilitate instruction, has grown into a full econometrics package that instructors can use as a research tool as well as an instructional aid.

Design/methodology/approach

The paper provides an overview of GRETL's accessibility and its capabilities. Next it addresses the use of GRETL for instructional purposes. Then it shows how GRETL can be used as a research tool.

Findings

The paper shows that GRETL can be a useful addition to the instructor who is showing novices how to use regression models. Also, it can be used as a research tool.

Practical implications

Given software like GRETL, instructors no longer need to omit model estimation because of the difficulties in accessing software and showing students how to use it.

Originality/value

This paper introduces a relatively new option, the use of a powerful open‐source software package to instructors in finance and accounting courses.

Details

Managerial Finance, vol. 36 no. 1
Type: Research Article
ISSN: 0307-4358

Keywords

Click here to view access options
Article
Publication date: 1 August 2001

Christian Janssen, Bo Söderberg and Julie Zhou

Real estate market data often contain outliers in the observations. Since outliers have a large influence on least squares estimates, robust regression methods have been…

Downloads
1997

Abstract

Real estate market data often contain outliers in the observations. Since outliers have a large influence on least squares estimates, robust regression methods have been recommended for this situation. Compares the performance of least squares and least median of squares, a robust method, in the estimation of price/income relationships for apartment buildings. Multiplicative models with multiplicative errors are estimated by means of natural log transformations. The study confirms the importance of employing robust methods for this application and implies this may well be so for real estate data sets more generally.

Details

Journal of Property Investment & Finance, vol. 19 no. 4
Type: Research Article
ISSN: 1463-578X

Keywords

Click here to view access options
Article
Publication date: 20 September 2021

Dang Luo and Decai Sun

With the prosperity of grey extension models, the form and structure of grey forecasting models tend to be complicated. How to select the appropriate model structure…

Abstract

Purpose

With the prosperity of grey extension models, the form and structure of grey forecasting models tend to be complicated. How to select the appropriate model structure according to the data characteristics has become an important topic. The purpose of this paper is to design a structure selection method for the grey multivariate model.

Design/methodology/approach

The linear correction term is introduced into the grey model, then the nonhomogeneous grey multivariable model with convolution integral [NGMC(1,N)] is proposed. Then, by incorporating the least absolute shrinkage and selection operator (LASSO), the model parameters are compressed and estimated based on the least angle regression (LARS) algorithm.

Findings

By adjusting the values of the parameters, the NGMC(1,N) model can derive various structures of grey models, which shows the structural adaptability of the NGMC(1,N) model. Based on the geometric interpretation of the LASSO method, the structure selection of the grey model can be transformed into sparse parameter estimation, and the structure selection can be realized by LASSO estimation.

Practical implications

This paper not only provides an effective method to identify the key factors of the agricultural drought vulnerability, but also presents a practical model to predict the agricultural drought vulnerability.

Originality/value

Based on the LASSO method, a structure selection algorithm for the NGMC(1,N) model is designed, and the structure selection method is applied to the vulnerability prediction of agricultural drought in Puyang City, Henan Province.

Details

Grey Systems: Theory and Application, vol. ahead-of-print no. ahead-of-print
Type: Research Article
ISSN: 2043-9377

Keywords

1 – 10 of over 24000