Alternative Methods of Regression

Birkes, David; Dodge, Yadolah

doi:10.1002/9781118150238

Cited by 290 publications

(213 citation statements)

References 0 publications

Supporting

Mentioning

184

Contrasting

Unclassified

Order By: Relevance

“…Application of the R program written for the algorithm to the data in Table 1 yielded the same results with the iterative method by Birkes and Dodge (1993). The best two data points are given to be at (x5, y5) and (x14, y14).…”

Section: Resultssupporting

confidence: 50%

“…The proposed method produced a least absolute deviation estimate that is the same as the one provided by the iterative method by Birkes and Dodge (1993) and other existing methods…”

Section: Resultsmentioning

confidence: 66%

“…Thus, the choice of estimation method under non-ideal conditions has been a long-standing problem for methodological researchers (Nevitt & Tam, 1998). The history of this problem is lengthy with many alternative estimation methods having been proposed and investigated (Birkes & Dodge, 1993).…”

Section: Algorithm and Code For Lad Estimator 756mentioning

confidence: 99%

“…LAD was developed by Roger Joseph Boscovich in 1757, nearly 50 years before OLS estimation (see Birkes & Dodge, 1993 for a review and historical citations). In contrast to OLS estimation which defines the loss function on the residuals as Σei 2 , LAD finds the slope and Y intercept that minimize the sum of the absolute values of the residuals, Σ | ei |.…”

Section: Algorithm and Code For Lad Estimator 756mentioning

confidence: 99%

See 3 more Smart Citations

An Alternative Algorithm and R Programming Implementation for Least Absolute Deviation Estimator of the Linear Regression Models

Ogundele¹,

Mbegbu²,

Nwosu³

2016

J. Mod. App. Stat. Meth.

View full text Add to dashboard Cite

show abstract

Section: Resultssupporting

confidence: 50%

“…The proposed method produced a least absolute deviation estimate that is the same as the one provided by the iterative method by Birkes and Dodge (1993) and other existing methods…”

Section: Resultsmentioning

confidence: 66%

Section: Algorithm and Code For Lad Estimator 756mentioning

confidence: 99%

Section: Algorithm and Code For Lad Estimator 756mentioning

confidence: 99%

See 2 more Smart Citations

An Alternative Algorithm and R Programming Implementation for Least Absolute Deviation Estimator of the Linear Regression Models

Ogundele¹,

Mbegbu²,

Nwosu³

2016

J. Mod. App. Stat. Meth.

View full text Add to dashboard Cite

show abstract

“…23 A similar approach was adopted by Falkenstein (2001), who addresses the non linearity feature of the ratios and the fact that these are sometimes not monotonically related to default adopting a nonparametric approach. 24 See Birkes and Yadolah (1993) who illustrate many nonparametric procedures which are based on using the rank of numbers instead of the numbers themselves.…”

Section: Rank Modelmentioning

confidence: 99%

An integrated multi-model credit rating system for private firms

Butera¹,

Faff

2006

Rev Quant Finan Acc

View full text Add to dashboard Cite

Abstract:The BIS 2001 opened the door to the possibility of using, subject to validation by the individual national supervisory authorities, systems of internal rating of credit risk developed by the banks when they satisfy certain criteria. Specifically, the Basel Committee proposed two approaches to the internal rating of credit risk -the 'foundation' and 'advanced' approaches. As such, there is a different degree of bank "autonomy" in the estimation of the parameters relevant to determining the risk weighting and thus to capital adequacy: there is lesser autonomy in the case of the 'foundation' approach and greater autonomy in the 'advanced' version. This paper presents a compound credit risk modelling approach for private firms which fulfil 2001 Basel Accord requirements in the case of the adoption of the foundation approach. We present findings from applying this model to a large sample of client firms of the Bank of Rome. An Integrated Multi-model Credit Rating System for Private Firms Abstract:The BIS 2001 opened the door to the possibility of using, subject to validation by the individual national supervisory authorities, systems of internal rating of credit risk developed by the banks when they satisfy certain criteria. Specifically, the Basel Committee proposed two approaches to the internal rating of credit risk -the 'foundation' and 'advanced' approaches. As such, there is a different degree of bank "autonomy" in the estimation of the parameters relevant to determining the risk weighting and thus to capital adequacy: there is lesser autonomy in the case of the 'foundation' approach and greater autonomy in the 'advanced' version. This paper presents a compound credit risk modelling approach for private firms which fulfil 2001 Basel Accord requirements in the case of the adoption of the foundation approach. We present findings from applying this model to a large sample of client firms of the Bank of Rome.

show abstract

The minimum sum of absolute errors regression: a robust alternative to the least squares regression

et al. 1999

View full text Add to dashboard Cite

This paper concerns the minimum sum of absolute errors regression. It is a more robust alternative to the popular least squares regression whenever there are outliers in the values of the response variable, or the errors follow a long tailed distribution, or the loss function is proportional to the absolute errors rather than their squared values. We use data from a study of interstitial lung disease to illustrate the method, interpret the findings, and contrast with least squares regression. We point out some of the problems with the least squares analysis and show how to avoid these with the minimum sum of absolute errors analysis.

show abstract

Alternative Methods of Regression

Cited by 290 publications

References 0 publications

An Alternative Algorithm and R Programming Implementation for Least Absolute Deviation Estimator of the Linear Regression Models

An Alternative Algorithm and R Programming Implementation for Least Absolute Deviation Estimator of the Linear Regression Models

An integrated multi-model credit rating system for private firms

The minimum sum of absolute errors regression: a robust alternative to the least squares regression

Contact Info

Product

Resources

About