|
|||||
|
|
Random Effect Threshold Models for Dose–Response Relationships with Repeated Measurements |
|
| Authors: | Per M Brockhoff & Hans-Georg Müller |
| Institution: | Royal Veterinary and Agricultural, University at Copenhagen, Frederiksberg, DK,;University of California, Davis, USA |
| Abstract: | A random threshold model for dose--response designs with repeated measurements is introduced. Inference procedures for this model are discussed. The framework of generalized linear models is used to propose a quasi-likelihood inference procedure. The feasibility of this approach is illustrated with the analysis of food science data concerning a forced choice sensory experiment. |
| Keywords: | binomial regression forced choice experiment generalized linear model iterated weighted least squares likelihood overdispersion quasi-likelihood sensory experiment variance component |