Belief elicitation with multiple point predictions

We propose a simple, incentive compatible procedure based on binarized linear scoring rules to elicit beliefs about real-valued outcomes - multiple point predictions . Simultaneously eliciting with incentives reveals the subjective probability distribution without pre-defined intervals or probabilistic statements. show that approach is theoretically as robust existing methods, while adapting flexibly different beliefs. In laboratory experiment, we compare our standard of discrete probabilities intervals. find elicitation faster, perceived less difficult and more consistent subsequent decision. further are accurate if vary between participants. Finally, provide experimental evidence anchor reports.