Ignacio Mauleón

Testing densities with financial data: an empirical comparison of the Edgeworth-Sargan density to the Student's t

The Edgeworth—Sargan density has been shown capable of capturing salient empirical regularities of financial data in some studies. The main purpose of the reported study is to compare its performance with other densities, most notably to the Student t. Both densities can account for thick tails, and asymmetry One important by product of the comparison is to test the existence of moments. The comparison of densities is carried out with daily financial observations, spanning 25 years of data from two major world stock markets. Attention is paid to the fitting of other empirical regularities, and especially to the peak, frequently found at the middle of the densities.

Financial densities in emerging markets: an application of the multivariate ES density

Abstract This paper derives and presents the multivariate Edgeworth–Sargan (ES) density, discusses some of its properties, and estimates it for three exchange rates in emerging markets (Chile, Hungary and Singapore). The ES density fits the data adequately, and the model is estimated simultaneously for all variables. This involves estimating a highly non-linear model with 32 parameters. A multivariate Students t is also estimated, and both sets of results are compared. The empirical results show that, (a) the ES density applies to emerging markets as well as to more developed economies, as shown in previous research, (b) it is feasible to estimate a multivariate density of large dimensionality, and (c) independent estimation of the marginal densities, although a consistent procedure, yields significantly different results from the multivariate estimation for some parameters.

Modelling multivariate moments in European Stock Markets

This research extends the results of Mauleón and Perote, and derives analytically a general framework for the multivariate Edgeworth Sargan (ES) density. Its capability to account for multivariate moments beyond correlation is shown–mainly, co-skewness, co-kurtosis and co-volatility. The multivariate ES is then fitted to the residuals of a VAR model applied to three European stock market series of daily data (FTSE, DAX, CAC40), accounting for univariate as well as multivariate departures from normality. The complete model – with nearly 60 parameters – is set up and estimated jointly by maximum likelihood. Two alternative multivariate probability density functions, students t and the normal skewed, are also estimated and compared to the ES. The empirical results show: (1) in spite of the high nonlinearity and complexity of the model, it is feasible to fit it to empirical data; (2) statistically significant multivariate effects, other than correlations, are found, and (3) the tail fit of the ES is significantly better.

The Cost of Renewable Power: A Survey of Recent Estimates

This paper presents the results of an overview and survey of recent, up-to-date estimates of the cost of generating electric power from renewables. The results are based on actual data from projects already implemented or commissioned, and are organised as homogeneously and comparably as possible. Two main cost measures are considered: total capital costs, and its two main components, equipment, and remaining installation costs, and the Levelised Cost of Electricity (LCOE). An extended discussion on the definition and meaning of this latter cost measure is also provided in an appendix. The chapter closes with some reflections and forecasts of the likely scenario for the power business in the coming years.

Modelling Interest Rates in the Long Run

This research addresses empirically mainly, the issue of the long run impact of the real Gdp growth rate on the real rate of interest. The model is based on growth theories, rather than in the savings-investment market, and implies a positive and close to one impact of real growth on the real interest rate. The results obtained for a sample starting from the end of World War II, for the UK and the US, broadly support the theoretical result. A negative impact of the real rate on Gdp growth, however, is not detected. An aggregate model is also estimated, yielding similar conclusions. A non linear development of the mixed-model estimation technique originally suggested by Durbin and Theil, is implemented to obtain several of the main results.

Growth and the current account: Malaysia and Singapore

A foreign trade model is estimated for two South East Asian countries, selected because they represent two extremes as far as the current account balance is concerned—Malaysia, deficit, Singapore, surplus. The specification highlights, (a) the simultaneous interdependence of exports and import flows—a result of what Krugman [1995] denotes as the slicing up of the production process—and, (b) the impact of investment on imports as a result of productivity shocks on the current account. The estimation results point to the instability of the market for foreign exchange. Using an intertemporal framework, a methodology to derive the external long run equilibrium is applied to the estimated model. The implied constraint on domestic growth turns out to be mild.