Descripción
|
|
---|---|
We investigate on trend-following trading strategies over a time series data of mining equities. These strategies are widely used in the investment world. We provide a set of sufficient conditions that determine the optimality of the traditional trend-following strategies when the trends are completely observable. The main driver of trend-following rules? profitability is return persistence, which in turn, is negatively related to market development. Nevertheless, the investors are always interested in forecasting future values. In this sense, the time series adjusted close diary data between January 2006 and November 2013 for 23 different mining equities have been analyzed with the aim of fit some forecasting model that allows estimate future values. Function autocorrelation is employed to analyze trends and other possible data periodicities. We use ARIMA models to predict type or exponential smoothing as serial or no correlation exists. The estimate is based on daily data from January 2006 to September 2013. The models are validated by obtaining predictions for the observed period through analysis of errors. For these data exponential smoothing models are more suitable for forecasting the ARIMA type, since trends or changes in the means of the observed values, are stabilized by taking differences, and no residual homoscedasticity is achieved. Despite being well known for its simplicity and accessibility models provide sufficiently reliable estimates for the future value data analyzed. | |
Internacional
|
Si |
Nombre congreso
|
ITISE 2014 International Work-Conference on Time Series Analysis |
Tipo de participación
|
960 |
Lugar del congreso
|
Granada |
Revisores
|
Si |
ISBN o ISSN
|
978-84-15814-97-9 |
DOI
|
|
Fecha inicio congreso
|
25/06/2014 |
Fecha fin congreso
|
27/06/2014 |
Desde la página
|
1316 |
Hasta la página
|
1316 |
Título de las actas
|
Proceedings ITISE 2014 International Work-Conference on Time Series Analysis |