Great Salt Lake (GSL) is the largest salt lake in the western hemisphere, the fourth-largest terminal lake in the world. The elevation of GSL has critical effect on the people who live nearby and their properties. It is crucial to build an exact model of GSL elevation time series in order to predict the GSL elevation precisely. Although some models, such as ARIMA or FARIMA (fractional auto-regressive integrated moving average), GARCH (generalized auto-regressive conditional heteroskedasticity) and FIGARCH (fractional integral generalized auto-regressive conditional heteroskedasticity) have been proposed to characterize the variation of GSL elevation, which have been unsatisfactory. Therefore, it became a key point to build a more appropriate model of GSL elevation time series. In this paper a new model based on FARIMA with stable innovations is applied to analyze the data and predict the future elevation levels. From the analysis we can see that the new model can characterize GSL elevation time series more accurately. The new model will be beneficial to predict GSL elevation more precisely.
- Hurst parameter;
- Long-range dependent;
- Stable distribution;
- FARIMA with stable innovations