Risk premia are difficult to identify in nonstorable commodities such as electricity. In this article, we propose a modified Fama–French regression framework and show that when the spot prices do not follow a martingale—a common assumption in the electricity market—model specifications play an important role in detecting time-varying risk premia in the futures market. With this insight, we propose a multi-factor model that captures important dynamics in electricity prices and an estimation method based on particle Markov chain Monte Carlo to separate risk factors in energy prices. Using spot and futures data in the Germany/Austria electricity market, we demonstrate that our proposed model surpasses alternative models that ignore some of risk factors in forecasting spot prices and in detecting time-varying risk premia. Based on our proposed model, we separately identify risk premia carried by individual risk factors and document large variations in the premia of each factor.

中文翻译：

---

识别风险因素及其溢价：电价研究

在电力等不可储存商品中，风险溢价难以识别。在本文中，我们提出了一个修正的 Fama-French 回归框架，并表明当现货价格不遵循鞅（电力市场中的一个常见假设）时，模型规范在检测期货中随时间变化的风险溢价中起着重要作用市场。有了这种认识，我们提出了一个多因素模型来捕捉电价的重要动态，以及一种基于粒子马尔可夫链蒙特卡罗的估计方法来分离能源价格中的风险因素。使用德国/奥地利电力市场的现货和期货数据，我们证明我们提出的模型在预测现货价格和检测随时间变化的风险溢价方面超越了忽略一些风险因素的替代模型。基于我们提出的模型，