Decisions regarding agricultural production involve multiple goals. A multicriteria approach allows decision makers to consider more aspects of the decision scenario, although it also leads to other problems, such as difficulties with the selection of goals or criteria, as well as assigning them appropriate weights. It is argued that not only do goals vary depending on the decision-makers' socioeconomic features, but their relative importance changes as well. A simulation study has been conducted based on the Farm Accountancy Data Network (FADN) database. We use the distance-to-the-negative-solution maximization model. Seven sets of criteria and different sets of weights are considered. The main purpose of the study is to determine the impact of weights on the quality of the model. Quality is assessed by comparing the optimal and observed values of the decision variables. The results lead to the conclusion that the differences between the quality of various models are small. (original abstract)