Showing 1 - 10 of 71
Grey system theory can powerfully deal with incomplete and uncertain information. In this paper, we introduced an improved grey GM(1,1) model that integrates residual modification with Markov chain model. By this model, we improved the forecast accuracy of original grey forecast model and...
Persistent link: https://www.econbiz.de/10009958471
Some researchers, for example, Koop [1], and Sims [2], have advocated for Bayesian alternatives to unit-root testing over the classical approach using the augmented Dickey-Fuller test (ADF). This paper studies the power of what Koop [1] has called the Objectiveʺ Bayesian approach to unit-root...
Persistent link: https://www.econbiz.de/10010080118
This paper extends previous studies in modeling and estimating energy demand functions for both gasoline and kerosene petroleum products for Nigeria from 1977 to 2008. In contrast to earlier studies on Nigeria and other developing countries, this study specifically tests for the possibility of...
Persistent link: https://www.econbiz.de/10010039587
. The out-of-sample forecasting performance of the TVP-VAR model is evaluated against the simple VAR and ARIMA models, by … consistently outperforms the simple VAR and ARIMA models. -- stock prices ; exchange rates ; bivariate causality ; forecasting …
Persistent link: https://www.econbiz.de/10009958060
-parametric approaches of seasonal adjustment. Then, we compare the forecasting performance of these methods. The empirical results militate … in favour of the TRAMO-SEATS method. In fact, this approach provides the best forecast. In terms of forecasting …
Persistent link: https://www.econbiz.de/10010148054
; temporal disaggregation ; forecasting ; nowcasting …
Persistent link: https://www.econbiz.de/10010030016
We study optimal hedging design for returns on an Italian equity mutual fund index since 2008. Alternative hedging instruments include one-month futures contracts for FTSE-MIB, FTSE100 and Xetra DAX. We use bivariate models of our Italian equity mutual fund index and each hedging instrument to...
Persistent link: https://www.econbiz.de/10010148077
This paper presents a study of Artificial Neural Network (ANN) and Bayesian Network (BN) for use in stock index prediction. The data from Nigerian Stock Exchange (NSE) market are applied as a case study. Based on the rescaled range analysis, the neural network was used to capture the...
Persistent link: https://www.econbiz.de/10010148286
This paper introduces a new parametric measure of productivity change using the hyperbolic distance function. More specifically, the paper first estimates a stochastic translog hyperbolic distance function, which satisfies regularity conditions, using the Bayesian approach. Then it derives an...
Persistent link: https://www.econbiz.de/10010058696
Using the maximum likelihood method, in order to estimate Half-Normal stochastic frontier production models, entails several practical di±culties that, perhaps, have not been su±ciently emphasised. In employing FRONTIER software, we analyse the case in which the estimation obtained suggests...
Persistent link: https://www.econbiz.de/10009957389