Related Experiment Videos
Analysis of pharmacokinetic data using parametric models. III. Hypothesis tests and confidence intervals
Journal of Pharmacokinetics and Biopharmaceutics
|October 1, 1986
Summary
This tutorial explains how to test hypotheses and create confidence intervals for pharmacokinetic model parameters. It uses goodness-of-fit measures to assess parameter plausibility and estimate parameter uncertainty.
Area of Science:
- Pharmacometrics
- Statistical modeling
- Pharmacokinetic analysis
Background:
- Parametric models are widely used for pharmacokinetic (PK) data analysis.
- Accurate parameter estimation and uncertainty quantification are crucial for PK studies.
- Previous articles in this series covered PK data analysis using parametric models.
Purpose of the Study:
- To provide methods for hypothesis testing regarding PK model parameters.
- To explain the process of assigning confidence intervals to PK model parameters.
- To guide researchers in assessing the plausibility of parameter values.
Main Methods:
- Utilizing goodness-of-fit (GOF) measures to evaluate model performance.
- Assessing parameter plausibility by analyzing changes in GOF with parameter variations.
- Employing a least-squares-type objective function to quantify GOF.
- Approximating the parameter-dependent objective function to estimate the asymptotic covariance matrix.
Main Results:
- The change in GOF serves as a metric for assessing parameter uncertainty.
- An estimated asymptotic covariance matrix provides insights into parameter interdependencies.
- This matrix facilitates hypothesis testing and confidence interval construction for parameters and their functions.
Conclusions:
- The described methods enable robust hypothesis testing for PK model parameters.
- Confidence intervals for PK parameters can be reliably generated.
- The approach enhances the statistical rigor of pharmacokinetic modeling and analysis.