Financial data analysis Essay Example | Topics and Well Written Essays - 1000 words

Financial data analysis - Essay Example A clear linear relationship is not evident, which could be an indicator that WHEATHD is a poor predictor of WHEATSF. Figure 1: the plot of WHEATSF against WHEATHD Model R R Square Adjusted R Square Std. Error of the Estimate Change Statistics R Square Change F Change df1 df2 Sig. F Change 1 .421a .177 .174 27.2183 .177 53.344 1 248 .000 Table1: Model regression summary Table 1 above presents a summary of the regression summary. From this, adjusted R squared is 0.17, a figure that is very small indicating that the model is not very good in predicting the dependent variable as it is highly subject to chance rather than statistical relationship between the two variables. However, the p-value is less than 0.01, an indicator that the model is statistically significant, or rather we have enough evidence to assert that WHEATHD has some predictive power on WHEATSF. Coefficientsa Model Unstandardized Coefficients Standardized Coefficients t Sig. B Std. Error Beta 1 (Constant) 500.582 24.519 2 0.416 .000 WHEATHD(P) -.443 .061 -.421 -7.304 .000 Table 2: a. Dependent Variable: WHEATSF(P) Coefficientsa Model Unstandardized Coefficients Standardized Coefficients t Sig. B Std. Error Beta 1 (Constant) 532.035 17.694 30.069 .000 WHEATSF(P) -.400 .055 -.421 -7.304 .000 Table 3: a. ... itable statistical technique to use, but I surmounted this by examining the expected outcome to decide on the best method (Hyndman and Koehler, 2006). PART II In this part, 1- 250 sample values are used to forecast the subsequent 11 values. Using excel to forecast In using excel spreadsheets to do the forecast, we highlight the raw data and insert the scatter plot. Then, we insert the trend line in the scatter plot and subsequently format it to include the trend line equation. The trend line equation is then used to substitute the values of x for the 11 series periods that are sampled for prediction. The following table shows the values of x and the substituted values y. Y=532.03-0.4x x Y (Forecasted) Actual 308.5 408.63 443 311.5 407.43 446.5 314.5 406.23 450 313.5 406.63 447 319.5 404.23 451.5 324.5 402.23 451.5 324.5 402.23 451.5 333.5 398.63 461.25 337.5 397.03 465.75 324.5 402.23 460.75 327.5 401.03 462.5 Sum 4436.53 4991.25 Figure 2: Excel scatter plot with the equation fitted in. Using eview The raw data for the prices are input in the software and a forecast generated automatically. The output, which is shown in figure 3, comes with a table with forecast errors already computed. The table alongside shows statistical arithmetic that is associated with this particular model, including a number of methods for calculating the forecasting errors. Figure 3: Forecast for 251 - 261 Sample Figure 4: graph before model 1forecast Figure 5: graph after model 1 forecast Forecast errors Forecast errors are the estimations of the probability that the results of the forecast deviates from the actual values. Fore example, looking at figures 4 and 5 of the first forecast model, it is clear how the forecast values differ slightly from the actual values. A number of errors that