Nonlinear least-squares regression analysis in pharmacokinetics: Application of a programmable calculator in model parameter estimation
โ Scribed by Keith T. Muir
- Publisher
- Elsevier Science
- Year
- 1980
- Tongue
- English
- Weight
- 570 KB
- Volume
- 13
- Category
- Article
- ISSN
- 0010-4809
No coin nor oath required. For personal study only.
โฆ Synopsis
Two programs allowing nonlinear least-squares fits to data conforming to the onecompartment oral and the two-compartment intravenous pharmacokinetic models are described. Model parameter estimates are obtained together with an estimate of the precision of these parameters. The method is based on the Gauss-Newton algorithm programmed onto a Texas Instruments TI 59 pocket programmable calculator and recorded on 7.5 x 1.5~cm magnetic cards. Comparisons with NONLIN show that the parameter estimates from both programs are essentially identical. The programs allow for a great reduction in computing costs and increased availability of data analysis facilities in phannacokinetics.
๐ SIMILAR VOLUMES
This paper investigates the efficiencies of several generalized least squares estimators (GLSEs) in terms of the covariance matrix. Two models are analyzed: a seemingly unrelated regression model and a heteroscedastic model. In both models, we define a class of unbiased GLSEs and show that their cov
The plasma or blood concentration profiles are fitted by single or two compartment open models using log-linear regression analyses. For two compartment models, "feathering" is performed at 95% equilibration time obtained from raw pharmacokinetic data. The equations have been programmed onto a Texas