Filling and D-optimal Designs for the Correlated Generalized Exponential Model
The aim of this paper is to provide guidelines for efficient statistical estimation of the parameters of the modified Arrhenius model for chemical kinetics. We study D-optimal and filling designs for this model, assuming correlated observations and exponential covariance with or without nugget effect. We consider both equidistant and exact designs for small samples, and study the behaviour of different types of filling designs when a greater number of observations is preferred.
KeywordsFisher Information Transition State Theory Nugget Effect Exact Design Transition State Theory
Unable to display preview. Download preview PDF.
- International Union of Pure and Applied Chemistry (IUPAC) (2008). Transition state theory. Technical report, http://goldbook.iupac.org/T06470.html.
- Jet Propulsion Laboratory (2006). Chemical kinetics and photochemical data for use in atmospheric studies, NASA panel for data evaluation. Technical report, California Institute of Technology, Pasadena, California.Google Scholar
- Müller, W. and M. Stehlík (2010). Compound optimal spatial designs. Environmetrics DOI: 10.1002/env.1009.Google Scholar
- Rodríguez-Aragón, L. and J. López-Fidalgo (2005). Optimal designs for the arrhenius equation. Chemometrics & Intelligent Laboratory Systems 77, 131–138.Google Scholar
- Rodríguez-Díaz, J., T. Santos-Martín, M. Stehlík, and H. Waldl (2009). Filling and d-optimal designs for the correlated generalized exponential models. Technical report, IFAS - JKU University.Google Scholar