Geometric View of Measurement Errors |
| |
Authors: | Diarmuid O'driscoll |
| |
Institution: | Department of Mathematics and Computer Studies , Mary Immaculate College , Limerick , Ireland |
| |
Abstract: | The slope of the best fit line from minimizing the sum of the squared oblique errors is the root of a polynomial of degree four. This geometric view of measurement errors is used to give insight into the performance of various slope estimators for the measurement error model including an adjusted fourth moment estimator introduced by Gillard and Iles (2005
Gillard , J. ,
Iles , T. ( 2005 ). Method of moments estimation in linear regression with errors in both variables, Cardiff University School of Mathematics Technical Report, Cardiff, Wales, UK . Google Scholar]) to remove the jump discontinuity in the estimator of Copas (1972
Copas , J. ( 1972 ). The likelihood surface in the linear functional relationship problem . Journal of the Royal Statistical Society. Series B (Methodological) 34 : 274 – 278 . Google Scholar]). The polynomial of degree four is associated with a minimun deviation estimator. A simulation study compares these estimators showing improvement in bias and mean squared error. |
| |
Keywords: | Maximum likelihood estimation Measurement errors Moment estimation Oblique errors |
|
|