The Composite Index of Leading Economic Indicators: How to Make it More Timely

51
A major shortcoming of the U.S. leading index is that it does not use the most recent information for stock prices and yield spreads. The index methodology ignores these data in favor of a time-consistent set of components (i.e., all of the components must refer to the previous month). An alternative is to bring the series with publication lags up-to-date with forecasts and create an index with a complete set of most recent components. This study uses tests of ex-ante predictive ability of the U.S. leading index to evaluate the gains to this new 'hot box' procedure of statistical imputation. We find that, across a variety of simple forecasting models, the new approach offers substantial improvements.


Mandelbrot Market-Model and Momentum

52
Mandelbrot has significantly contributed in many ways to the area of finance. He was one of the first who criticized the oversimplifications centered around the early stochastic process models of Bachelier utilizing normal distribution. In his view, markets were fractal and much wilder than classical theory suggests. Additionally, he was a profound critic of the efficient markets hypothesis. Particularly, his work of fractional Brownian motion showed that the independence claim made by that hypothesis is not valid; in addition, he proposed a multi-fractal asset model to reconcile for effects observed in the market. However, it is also known that his vision of fractal markets used fractal trends. Recently, we were able to show that the scaling behaviour of trends, as defined by a specific trend decomposition using wavelets, are the root cause for the momentum effect.

Additionally, we were able to show that these trends have fractal characteristics. In this work, we will revisit Mandelbrot’s vision of fractal markets. We will show that the momentum effect discussed heavily in literature can be modeled by the so-called Mandelbrot Market-Model. Additionally, this model shows, from the risk side, that markets are wilder because of trend structures compared with classical models. In conclusion, we derive what Mandelbrot always knew: There are no efficient markets.

MATLAB Routines for Moving Median with Trend and Seasonality for Time Series Prediction

53
In this paper we provide a simple MATLAB routine which computes the moving median with trend and seasonality. This approach is linear and for this reason has its disadvantages. So this routine can be improved by combining Monte-Carlo simulations, genetic algorithms simulations and wavelets decomposition.

Feed-Forward Neural Networks Regressions with Genetic Algorithms: Applications in Econometrics and Finance

54
In this paper we examine feed-forward neural networks using genetic algorithms in the training process instead of error backpropagation algorithm. Additionally real encoding is preferred to binary encoding as it is more appropriate to find the optimum weights. We use learning and momentum rates for the weight updating as in the case of the error backpropagation algorithm. Some empirical examples as well as the programming routine in MATLAB are provided.


Who is online

Users browsing this forum: No registered users and 17 guests