Corrado Corradi

A note on interest rate term structure estimation using tension splines

Abstract Tension splines are proposed as a flexible tool for interest rate term structure estimation to circumvent some difficulties arising with the ordinary cubic spline estimators. A few computational experiments on test problems support the merits of the proposed approach.

Smooth distributed lag estimators and smoothing spline functions in Hilbert spaces

Abstract The theoretical connections between smooth distributed lag estimators and smoothing spline functions in Hilbert spaces are investigated. Shillers estimator is obtained as a special case of smoothing spline. An extension of Shillers approach is presented utilizing some results from functional analysis.

A note on the computation of maximum likelihood estimates in linear regression models with autocorrelated errors

Abstract In this note we propose a modification of the Cochrane-Orcutt iterative procedure for the computation of maximum likelihood estimates in a linear regression model with autocorrelated disturbances which possesses faster asymptotical convergence rate. The theoretical properties are shown to be supported by experimental results.

Computational experience with algorithms for separable nonlinear least squares problems

Nonlinear least squares problems frequently arise in which the fitting function can be written as a linear combination of functions involving further parameters in a nonlinear manner. This paper outlines an efficient implementation of an iterative procedure originally developed by Golub and Pereyra and successively modified by various authors, which takes advantage of the linear-nonlinear structure, and investigates its performances on various test problems as compared with the standard Gauss-Newton and Gauss-Newton-Marquardt schemes.

On the estimation of smooth forward rate curves from a finite number of observations: A comment

Abstract The problem of estimating the forward rate curve from observed values of the yield-to-maturity is considered in the context of the theory of spline functions in Hilbert spaces and the solution is given in the interpolatory and smoothing case.

A Note on the Solution of Separable Nonlinear Least-Squares Problems with Separable Nonlinear Equality Constraints

A modification is described to the numerical method proposed by Kaufman and Pereyra [SIAM J. Numer. Anal., 15 (1978), pp. 12–20] for the solution of separable nonlinear least-squares problems with separable nonlinear equality constraints by showing how this problem can be reduced to a separable unconstrained problem having a simpler structure. A computational procedure is then proposed based on the generalized

Pricing Equity and Debt Tranches of Collateralized Funds of Hedge Fund Obligations: an approach based on Stochastic Time Change and Esscher Transformed Martingale Measure

LU

Valuation of Collateralized Funds of Hedge Fund Obligations: A Basket Option Pricing Approach

decomposition of the matrix of the constraint equations.

Monotonicity preserving regression techniques for interest rate term structure estimation: A note

Collateralized Funds of Hedge Fund Obligations (CFOs) are relatively recent structured finance products linked to the performance of underlying funds of hedge funds. The capital structure of a CFO is similar to traditional Collateralized Debt Obligations (CDOs), meaning that investors are offered different rated notes and equity interests. CFOs are structured as arbitrage market value CDOs. The fund of funds manager actively manages the fund to maximize total returns while limiting price volatility within the guidelines of the structure. The aim of this paper is to provide a useful framework to evaluate Collateralized Funds of Hedge Fund Obligations, that is pricing the equity and the debt tranches of a CFO. The basic idea is to evaluate each CFO liability as an option written on the underlying pool of hedge funds. The value of every tranche depends on the evolution of the collateral portfolio during the life of the contract. Care is taken to distinguish between the fund of hedge funds and its underlying hedge funds, each of which is itself a portfolio of various securities, debt instruments and financial contracts. The proposed model incorporates skewness, excess kurtosis and is able to capture more complex dependence structures among hedge fund log-returns than the mere correlation matrix. With this model it is possible to describe the impact of an equivalent change of probability measure not only on the marginal processes but also on the underlying dependence structure among hedge funds.

Optimal Control of Econometric Models: Some Experimental Results for the Italian Monetary Sector

The purpose of the present contribution is to provide an extension to a model developed by Tassinari and Corradi [7] to price equity and debt tranches of collateralized funds of hedge fund obligations (CFOs). The key idea is to price each CFO liability as an option on the underlying basket of hedge funds. The proposed model is able to reproduce the empirical characteristics observed in the distribution of hedge funds’ returns: skewness, excess kurtosis and dependence in the tails. Additionally, it can be easily calibrated to the empirical correlation matrix and it requires only historical information to be estimated and implemented. The result is a scheme that can be useful in structuring a CFO. In particular, we believe that the approach described in this work can be helpful to rating agencies and to deal structures to evaluate various capital structures, test levels, liquidity profiles, coupons and equity distribution rules.