Sensitivity analysis has been done in order to calculate impact of different independent value on the dependent value. In the given case for sensitive analysis the parameters for faster growth has been changed while the operating cost has been increases to pound 355,000/- . The result of sensitive analysis has been calculated in the excel sheet (Q.2).
The result conclude that as the price increases from 8th year the option 3 which was profitable from previous calculation become loss generating. From the 8thyear, the price of electricity increases to £0.012 under the faster growth scenario and decreases to £0.010 under the slower growth scenario. With the constant price of electricity option 1 become more profitable instead of option 3. Option 2 is still not a viable option.
Multiple regression analysis can be used as an alternative tool for predicting the value of dependent variable for the two or more dependent variables. The multiple regression equation used for the same is as follows –
Y = a0 + b1 X1 + b2 X2 + …………………… + bk Xk
Here a0 stands for intercept while b …bk stands for regression slope. The appropriateness of multiple models can be tested with the help of f-test. A significant F will indicate linear relationship between the x and y variables. The coefficient of R2 provides the predictive ability of a linear equation. Value of R2 lies between 0 to 1.
R2 – coefficient of determination
To closer the value of R2to 1, better predictive ability the equation will be. The other main question to be addressed is whether the independent variables individually or combined impact the dependent variable. It can be done by testing the null hypothesis with relevant regression coefficient to be zero. The value can be determined by t-test where regression coefficient is being tested. It is done by testing the null hypothesis that the regression coefficient value is zero.
The multiple regression has main limitation as it cannot test the linearity of the data, it assume a linear relationship between the variables. Secondly, the independent variables are not related to oneself multiple regression analysis. The correlation coefficient of independent variable though can be used to establish the relation.
The other option used in forecasting is sensitivity analysis. Sensitivity analysis can be one only with the help of data table in excel. It also predicts the change in dependent variable for change in independent variables. Importance of sensitivity analysis can be summarized as follows-
It’s a future prediction technique which put credibility to the predicted data.
It provides a range of output which provides flexibility to the prediction.
It is the insight to scenarios as the dependence and interdependence variables.
It helps in decision making.
In the present case, the prediction made through multiple regression technique and sensitivity analysis has been taken in account for forecasting. Various alternatives have been evaluated and results has been taken in account in excel sheet (DEMAND PREDICTION).