Abstract
The presence of left censoring in environmental and engineering applications complicates tests of hypotheses and interval estimation. First, we construct a confidence interval (CI) for a true concentration using nonlinear mixed-effects regression models for analysis of interlaboratory calibration data with left censoring. Next, we impute the unobserved left-censored data with randomly simulated value. Finally, we compute the coverage probability via simulation and show that our methodology achieves the nominal level. We illustrate our methodology with a real-life example.
Original language | English |
---|---|
Pages (from-to) | 181-189 |
Number of pages | 9 |
Journal | Environmetrics |
Volume | 20 |
Issue number | 2 |
DOIs | |
State | Published - Mar 2009 |
Keywords
- Censored data
- Confidence interval
- Environmental monitoring
- Interlaboratory testing