Forecasting Methods

Forecasting Methods

Sensitivity analysis is a study that allows allocation and division of mathematical model outputs. In the presence of uncertainty, sensitivity analysis tests the strength of results and further understanding of input and output data relationship. Various forecasting methods are discussed in this paper, clearly stating their advantages and disadvantages.

Forecasting methods are used in giving results for sensitive analysis and regression. There are four techniques used including straight line, moving average, simple linear regression and multiple linear regressions. Depending on the nature of results data, each method is applied differently (Ren, Suganthan & Srikanth, 2014). For example, simple linear regression is used to compare one dependent variable with an independent one while moving average is used for repeated forecasts. This is one of a common limitation for these methods; they are specific to certain data. Weighted average has a greater advantage over the simple moving average in that it shows more accuracy in measuring recent price action for traders.

For multiple regressions, the method allows one to determine the relative influence of predictor variables to a criterion value. Another advantage is that outliers are easily identified in the multiple regression method (Inman, Pedro & Coimbra, 2013). This helps to narrow down data to best fit, making interpretation simple. The disadvantage of using multiple regression method is that one ends up using data, which is sometimes incomplete. This leads to false conclusions that correlation is causation.

Conclusion

Sensitive analysis and regression methods are used in solving mathematical problems.  It is important to select the method of analysis wisely based on the nature of data being investigated for accurate and reasonable results (Diagne, David, Lauret,  Boland,  & Schmutz, 2013).

References

Diagne, M., David, M., Lauret, P., Boland, J., & Schmutz, N. (2013). Review of solar irradiance forecasting methods and a proposition for small-scale insular grids. Renewable and Sustainable Energy Reviews, 27, 65-76.

Inman, R. H., Pedro, H. T., & Coimbra, C. F. (2013). Solar forecasting methods for renewable energy integration. Progress in energy and combustion science, 39(6), 535-576.

Ren, Y., Suganthan, P. N., & Srikanth, N. (2014). A comparative study of empirical mode decomposition-based short-term wind speed forecasting methods. IEEE Transactions on Sustainable Energy, 6(1), 236-244.