Linear and nonlinear filtering in finance

Add to your list(s) Download to your calendar using vCal

• Paresh Date, Department of Mathematical Sciences, Brunel University
• Wednesday 02 December 2009, 14:00-15:00
• CAP Seminar Room .

If you have a question about this talk, please contact Eric C Kerrigan.

Consider a possibly vector-valued system of discrete time equations X(k+1) = f(X(k), v(k)), Y(k) = g(X(k), w(k)), where v(k), w(k) are i.i.d. random sequences, g,f are well-behaved functions in an appropriate sense, Y(k) is a measured sequence and unobservable variable X(k) needs to be inferred from the measured value of Y(k). Problems of this type (or their continuous time analogues) are generically called filtering problems and they have applications in many branches of science including control engineering, signal processing, econometrics and finance. This work presents a review of time series filtering. A summary of recent empirical applications of linear filtering with real market data are presented for stochastic volatility modelling and yield curve modelling. Some numerically tractable approaches to filtering in nonlinear time series or in nonlinear input output systems, which have emerged independently from different branches of science (including engineering and climatology), are outlined, along with the challenges for systems theorists in this area of research.

This talk is part of the Control and Power Seminars series.

This talk is included in these lists:

• Andrea Picciau's list
• CAP Seminar Room
• COMMSP & CP list
• COMMSP Seminar
• Control and Power Seminars
• Featured talks
• SAP Talks

Note that ex-directory lists are not shown.