Purpose - Usually, people's interests do not match perfectly. So when several people need to make a joint decision, they need to compromise. The more people one has to coordinate the decision with, the fewer chances that each person's preferences will be properly taken into account. Therefore, when a large group of people need to make a decision, it is desirable to make sure that this decision can be reached by dividing all the people into small-size groups so that this decision can reach a compromise between the members of each group. The study's objective is to analyze when such a compromise is possible. Design/methodology/approach - In this paper, the authors use a recent mathematical result about convex sets to analyze this problem and to come up with an optimal size of such groups. Findings - The authors find the smallest group size for which a joint decision is possible. Specifically, the authors show that in situations where each alternative is characterized by n quantities, it is possible to have a joint decision if the participants are divided into groups of size n - and, in general, no such decision is possible if the participants are divided into groups of size n - 1. Originality/value - The main novelty of this paper is that, first, it formulates the problem, which, to the best of the authors' knowledge, was never formulated in this way before, and, second, that it provides a solution to this problem. Purpose - Important research once thought unassailable has failed to replicate, Not just in economics, but in all science, The problem is therefore not in dispute nor are some of the causes, like low power, selective reporting, the file drawer effect, publicly unavailable data and so forth, Some partially worthy solutions have already been offered, like pre-registering hypotheses and data analysis plans. Design/methodology/approach - This is a review paper on the replication crisis, which is by now very well known. Findings - This study offers another partial solution, which is to remind researchers that correlation does not logically imply causation, The effect of this reminder is to eschew "significance" testing, whether in frequentist or Bayesian form (like Bayes factors) and to report models in predictive form, so that anybody can check the veracity of any model, In effect, all papers could undergo replication testing. Originality/value - The author argues that this, or any solution, will never eliminate all errors
