Testing for heterogeneity of preferences in randomized experiments: a satisfaction-based approach applied to multiplayer prisoners’ dilemmas

ABSTRACT

We use experimental data from the ‘vote with the wallet’ multiplayer prisoner’s dilemma to investigate with a finite mixture approach the effect of a responsible purchase on players’ satisfaction. We find clear-cut evidence of heterogeneity of preferences with two groups of players that differ significantly in terms of effects of the responsible choice on satisfaction.

KEYWORDS:

• Randomized experiment
• multiplayer prisoners’ dilemma
• mixture models
• satisfaction

JEL CLASSIFICATION:

• C92
• D03
• D12
• D60
• D71

Disclosure statement

No potential conflict of interest was reported by the authors.

Supplemental data

Supplemental data for this article can be accessed here.

Notes

¹ GameSat is measured by asking to participants at the end of each period the question ‘On a scale from 0 to 10, please indicate your level of satisfaction about the experience of the game’ and OtherSat by asking the question ‘On a scale from 0 to 10, please indicate your level of satisfaction about other players’ behaviour in the game’.

² Error in beliefs is measured as expectation on the number of buyers of good R minus the true number of buyers of good R.