Industries Services

Calculating the density and distribution function for the singly and doubly noncentral F

Saddlepoint approximation and bootstrap inference for the Satterthwaite class of ratios

Computing moments of ratios of quadratic forms in normal variables

Description: 

The accuracy and speed of numerical methods for computing the moments of a ratio of quadratic forms in normal variables is examined, with particular application to the sample autocorrelation function. Methods based on a saddlepoint approximation are demonstrated to be not only superior to existing approximations, but are numerically reliable and virtually as accurate as the method suitable for exact computations, while taking only a fraction of the time to compute. The new method also maintains its accuracy for time series models near the nonstationary border, which is of significant interest for unit-root inference and also a case for which first-order mean and variance approximations break down. As a wide variety of test statistics and their power functions arising in econometric models are expressible in the general form considered, the method should prove very useful for data analysis and model building.

Mixed normal conditional heteroskedasticity

Modeling higher frequency macroeconomic data: an application to German monthly money demand

A new approach to markov-switching GARCH models

Comment on William C. Brainard and Herbert E. Scarf's "How to Compute Equilibrium Prices in 1891"

Description: 

Bill and Herb have provided an illuminating and interesting presentation of Irving Fisher's Ph.D. dissertation Mathematical Investigations in the Theory of Value and Prices. They correctly emphasize that Fisher's fundamental contribution to the early theory of general equilibrium was the construction of a machine to compute the equilibrium quantities in a Walrasian model of competitive markets. As Fisher notes, Walras deserves priority for deriving a system of equations that characterize equilibrium in competitive markets. Even in this area, however, Fisher makes a subtle and interesting contribution in his system of equilibrium equations, discussed later.
The first modern treatment of computing equilibrium prices in Walrasian economies is due to Herb, as everyone in this audience knows. His seminal paper, “On the Computation of Equilibrium Prices,” appears, most appropriately, in Ten Essays in Honor of Irving Fisher. The modern treatment of the existence question in the general equilibrium model, due to Arrow and Debreu, converts the equilibrium conditions into a fixed point of a continuous map, say from the price simplex into itself. It follows from Brouwer's fixed point theorem that this map will have a fixed point. The Scarf algorithm computes approximate fixed points of any continuous map of the simplex into itself. Hence the Scarf algorithm can be used to compute equilibrium quantities.
Subsequent to Scarf's research, a more direct method of solving nonlinear systems of equilibrium equations was suggested by Eaves. The so-called homotopy method deforms a set of equations whose solution we know into the equilibrium equations, tracing out a path of solutions terminating in a solution for the equilibrium equations. Unfortunately, there is no price-adjustment interpretation of the disequilibrium prices along the homotopy path. In this way they are similar to the prices generated by the Fisher machine out of equilibrium.
Below we give a system of equations characterizing equilibrium in an exchange economy with two agents and three goods. Agents are assumed to be endowed with money income and additive separable utility functions, which are monotone, strictly concave, and smooth. The unknowns in our equations are the state variables of Fisher's machine, in other words, prices, individual consumptions, expenditures, marginal utilities of income, and marginal utilities of the consumptions implied by expenditures and prices. Equilibrium values are computed using the homotopy method.

Reply to 'Asset Trading Volume in Innite-Horizon Economies with Dynamically Complete Markets and Heterogeneous Agents: Comment'

Description: 

In a comment, Peter Bossaerts and William R. Zame [2006. Finance Research Letters. This issue] claim that the main result of our paper [Judd, K.L., Kubler, F., Schmedders, K., 2003. The Journal of Finance 58, 2203–2217], namely the no-trade theorem for the dynamic Lucas infinite horizon economy with heterogeneous agents, is an artifact of the assumption that asset dividends and individual endowments follow the same stationary finite-state Markov process. In this reply, we clarify our assumptions and contrast them with the examples in Bossaerts and Zame.

Modeling and predicting market risk with Laplace-Gaussian mixture distributions

Accurate value-at-risk forecasting based on the Normal-GARCH model

Description: 

A resampling method based on the bootstrap and a bias-correction step is developed for improving the Value-at-Risk (VaR) forecasting ability of the normal-GARCH model. Compared to the use of more sophisticated GARCH models, the new method is fast, easy to implement, numerically reliable, and, except for having to choose a window length L for the bias-correction step, fully data driven. The results for several different financial asset returns over a long out-of-sample forecasting period, as well as use of simulated data, strongly support use of the new method, and the performance is not sensitive to the choice of L.

Pages

Le portail de l'information économique suisse

© 2016 Infonet Economy

Subscribe to RSS - Industries Services