We suggest using D-efficient experimental designs for conjoint and discrete-choice studies, and discuss orthogonal arrays, nonorthogonal designs, relative efficiency, and nonorthogonal design algorithms. We construct designs for a choice study with asymmetry and interactions and for a conjoint study with blocks and aggregate interactions.∗

Policymakers committed to inducing technological change need information about the Likely effects of alternative policies, potential adoption rates of clean technologies, and costs to society in the long run. My goal was to use a "hybrid energy economy model (CIMS), which combines a degree of behavioural realism, technological explicitness, and economy-wide feedback capabilities, to develop pol...