Using Choice Experiment to Estimate Consumer Valuation: the Role of Experiment Design and Attribute Information Loads

With fixed dimensionality of choice experiments, previous simulation results shows that D-optimal design with correct priori information generates more accurate valuation. In the absence of prior information, random designs and designs incorporate attribute interactions result in more precise valuation estimates. In this paper, the Monte Carlo results demonstrate that the performances of different design strategy are affected by attribute information loads in choice experiments. Consumer valuation estimates in simulation settings varies with the number of attributes.