This paper considers linear rational expectations models in the frequency domain under general conditions. The paper develops necessary and sufficient conditions for existence and uniqueness of particular and generic systems and characterizes the space of all solutions as an affine space in the frequency domain. It is demonstrated that solutions are not generally continuous with respect to the parameters of the models, invalidating mainstream frequentist and Bayesian methods. The ill-posedness of the problem motivates regularized solutions with theoretically guaranteed uniqueness, continuity, and even differentiability properties. Regularization is illustrated in an analysis of the limiting Gaussian likelihood functions of two analytically tractable models.
翻译:本文件在一般条件下考虑了频率领域的线性合理预期模型。本文件为特定和通用系统的存在和独特性提出了必要和充分的条件,并将所有解决办法的空间定性为频率领域的近似空间。文件表明,就模型参数而言,解决办法一般不是连续的,使主流常客和巴耶斯方法无效。问题的不正确性促使以理论上保证的独特性、连续性、甚至差异性能的正规化解决方案。常规化体现在对两种可分析可移动模型的有限高斯概率功能的分析中。