Robustness to Non-Normality of Perpendicular Least Square Estimator of a Slope Parameters | ||||
| The Egyptian Statistical Journal | ||||
| Article 9, Volume 34, Issue 1, June 1990, Page 187-192 PDF (2.56 MB) | ||||
| Document Type: Original Article | ||||
| DOI: 10.21608/esju.1990.427524 | ||||
 View on SCiNiTO | ||||
| Authors | ||||
| G.M. EL-Sayyad* ; B.M. Assas* ; M. Atiqliah* | ||||
| Department of Statistics, King Abdulaziz University, Jeddah, Saudi Arabia | ||||
| Abstract | ||||
| Robustness to nonnormality is studied of slope estimator of a straight line fitted by minimising the sum of squares of deviations perpendicular to the line when both variables are subject to errors, nonnormal, and also true valuesof the linear relationship follow a nonnormal distribution. It is shown that the slope estimator is fairly insensitive to nonnormality of the true values and likely to be little affected by nonnormality of the error-distributions having equal variances. Besides, sen-sitivity to departure from equality of error variances is examined. Some key words: Asymptotic distribution, Functional relationship. Robustness to nonnormality: Structural relation-ship. | ||||
|
Statistics Article View: 16 PDF Download: 6 |
||||
