Abstract
We show that a non-linear representation of a straight line model provides an opportunity for achieving reasonable interval estimates of the X-intercept when straight line model methods fail to allow such an interval. Further, we show that non-linear methods are reasonable competitors to the standard straight line method in Graybill (1976), even when the straight line method gives an estimate. The advantage of the non-linear approach is that the intervals may be directly obtained by using standard statistical packages such as SAS®. No extra programming is required.
| Original language | English |
|---|---|
| Pages (from-to) | 1093-1115 |
| Number of pages | 23 |
| Journal | Communications in Statistics Part B: Simulation and Computation |
| Volume | 27 |
| Issue number | 4 |
| DOIs | |
| State | Published - 1 Jan 1998 |
Keywords
- Asymptotics simulation
- Calibration
- Inverse regression
- Least squares
ASJC Scopus subject areas
- Statistics and Probability
- Modeling and Simulation
Fingerprint
Dive into the research topics of 'Interval estimate for the X-intercept of a straight line: A nonlinear approach'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver