Answers are grounded in this paper and cite their sources.
The authors develop a dynamic consideration set formation model, complementary to the static model developed by Roberts and Lattin (1991). The model does not require direct consumer reports of consideration and therefore can be applied to scanner data. Explicitly incorporating consideration effects appears to improve the multinomial logit model significantly.
No takes yet. Share an insight, caveat, or question.
Andrews et al. (1995) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: