Skip to main content
ARS Home » Research » Publications at this Location » Publication #270728
Title: Estimation of dose-response models for discrete and continuous data in weed science

Author
item PRICE, WILLIAM - University Of Idaho
item SHAFII, BAHMAN - University Of Idaho
item Seefeldt, Steven

Submitted to: Weed Technology
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 3/6/2012
Publication Date: N/A
Citation: N/A

Interpretive Summary: Statisticians knew for over 80 years what the best method was to measure the impact of a chemical on a living organism. However, the mathematical computations involved were too time consuming so alternative, less accurate, methods were devised. Recent advances in computer speeds now make analyzing dose-response using the best theoretical method (maximum likelihood) possible using a standard computer. This manuscript instructs the reader on how to correctly use this method, giving demonstrations of the techniques for continuous and discrete data, and providing SAS code.

Technical Abstract: Dose-response analysis is widely used in biological sciences and has application to a variety of risk assessment, bioassay, and calibration problems. In weed science, dose-response methodologies have typically relied on least squares estimation under an assumption of normality. Advances in computational abilities and available software, however, have given researchers more flexibility and choices for data analysis when these assumptions are not appropriate. This paper will explore these techniques and explain their advantages in order to provide researchers with an up-to-date set of tools necessary for analysis of dose-response problems. Demonstrations of the techniques are provided using a variety of data examples from weed science.