10.
8a. t ratio = 805/258 = 3.12
8b. 68.4% variation. R squared explains the variation in dependent variable, explained by
changes in indpendent variables
8c. as regression equation, Salary = 20,720 + 805*20 = 36,820
8d. 95% CI
9.
MAPE 12.16 %
The slope is -88.76
To find sales in year 11, we take -88.76 and multiply by 2011. We add this number to 179,153.12
to find the answer below
179,153.12+(-88.76*2011) = 656.76 predicted sales for 2011
This simple line graph is used to compare the actual values verses the forecasted values.
10c. Monthly booking of another city with income $39,020 is found by the following equation:
371.675 + 0.01981* 39,020
371.675 + 756.246 = $1,127.92
The forecast of the location with the 39,020 income is rounded to $1,128 per month.
From the excel table, we can see that the intercept will be 371.6758 and the slope of the
income will be 0.01981
11.
We see a pretty clear trend in the graph with the sales. There is some mild variation as well.
Perhaps using a linear trend during the forecasting process would be helpful.
Similar to a previous question, Sales = 87587.1654 + 5296.9566*Time
11d.
11e. The MAPE is found to be 22,932 after using the formula and rounding to the nearest whole
number.
14. Equation is as follows:
DTE = 5 + b*DPI
14b. DPI = 19,648
So the point estimate will be 4,876.84 as the DTE for Illinois.
The SSE is 1,520.6798
95% confidence interval for the DPI = 1,835.48 to 7,918.20
14c. The percentage error in the forecast in this example would be -37.11% found by
4,876.84 - 7,754 / 7,754 * 100% = -37.11%
