学术文献库

High-frequency financial data can be collected as a sequence of curves over time; for example, as intra-day price, currently one of the topics of greatest interest in finance. The Functional Data Analysis framework provides a suitable tool to extract the information contained in the shape of the daily paths, often unavailable from classical statistical methods. In this paper, a novel goodness-of-fit test for autoregressive Hilbertian (ARH) models, with unknown and general order, is proposed. The test imposes just the Hilbert-Schmidt assumption on the functional form of the autocorrelation operator, and the test statistic is formulated in terms of a Cramér-von Mises norm. A wild bootstrap resampling procedure is used for calibration, such that the finite sample behavior of the test, regarding power and size, is checked via a simulation study. Furthermore, we also provide a new specification test for diffusion models, such as Ornstein-Uhlenbeck processes, illustrated with an application to intra-day currency exchange rates. In particular, a two-stage methodology is proffered: firstly, we check if functional samples and their past values are related via ARH(1) model; secondly, under linearity, we perform a functional F-test.