The solutions or states of optimization problems or simulations are evaluated by using objective functions. The weights for these objective functions usually have to be estimated from experts' evaluations, which are likely to be qualitative and somewhat subjective. Although such estimation tasks are normally regarded as quite suitable for machine learning, we propose a mathematical programming-based method for better estimation. The key idea of our method is to use an ordinal scale for measuring paired differences of the objective values as well as the paired objective values. By using an ordinal scale, experts' qualitative and subjective evaluations can be appropriately expressed with simultaneous linear inequalities, and which can be handled by a mathematical programming solver. This allows us to extract more information from experts' evaluations compared to machine-learning-based algorithms, which increases the accuracy of our estimation. We show that our method outperforms machine-learning-based algorithms in a test of finding appropriate weights for an objective function.