Andrew Chou Jeremy Cooperstock y Ran El--Yaniv z Michael Klugerman x Tom Leighton -- November, 1993 Abstract The distributional approach and competitive analysis have traditionally been used for the design and analysis of on-line algorithms. The former assumes a specific distribution on inputs, while the latter assumes inputs are chosen by an unrestricted adversary. This paper employs the statistical adversary (recently proposed by Raghavan) to analyze and design on-line algorithms for two-way currency trading. The statistical adversary approach may be viewed as a hybrid of the distributional approach and competitive analysis. By statistical adversary, we mean an adversary that generates input sequences, where each sequence must satisfy certain general statistical properties. The on-line algorithms presented in this paper have some very attractive properties. For instance, the algorithms are money-making; they are guaranteed to be profitable when the optimal off-li...

In this paper, we propose a bounded influence estimation (BIE) and outlier detection procedure for GARCH models. Previous studies show that maximum likelihood estimates of GARCH models are sensitive to outliers and financial time series present a heavy tail due to outliers. The proposed BIE limits the influence of a small subset of the data and is asymptotically normal. Its robustness against outliers and model misspecification is examined and supported. We further use BIE with GARCH models to develop a method for detection of additive outliers. An application to the exchange rates of major currencies is provided.