Question

Assume you are analyzing a time series of 12 observations. Using a 3-period moving average, you successfully calculate the Mean Absolute Error (MAE), Mean Square Error (MSE), and Mean Absolute Percentage Error (MAPE) for each forecasted time period. You then sum the error calculations for each time period for each of the three error calculation techniques respectively. You end up with: MAE 53.5, MSE 547.25, and MAPE 44.15%. To complete your error calculation and compare the accuracy of the 3-period MA to a different forecasting technique, what number do you need to divide each error calculation by? Week Demand (Units of 0+ blood) 38 1 45 43 52 4 41 36 40 7 43 O9 10 11 12 None of the above How many dummy variables appear in this model, and what categorical variables do they represent? You are projecting future sales and have constructed a linear model using historical sales data for each of the four quarters between years 2011 and 2014. Answer questions 24-28 using the information below Regression Statisties Multiple R Obs Quarter Year Sales Sales 1 2011 71 0.995 2011 49 R Square 0.990 90 2011 58 Adjusted R Square 0.986 80 4 4 2011 78 Standard Error 1561 70 2012 68 5 1 Observations 16 60 2012 41 7 2012 55 50 ANOVA 8 4 2012 73 40 df 2013 62 30 10 2013 38 Regression 4 20 11 2013 53 Residual 11 10 12 4 2013 70 Total 15 C 2014 13 1 59 7 8 9 10 11 12 13 14 15 16 14 2014 32 Coefficient 15 2014 50 Sales Intercept 81.75 4 16 2014 65 S1 -9.575 17 1 2015 S2 -33.55 18 2015 19 2015 S3 -18.525 20 2015 Time -1.025 4, the number of years contained in the model 4, the number of seasons contained in the model There are 3 dummy variables used to differentiate between 4 seasonal effects 3, seasons, years, and time None of the answers above are correct You are projecting future sales and have constructed a linear model using historical sales data for each of the four quarters between years 2011 and 2014. Answer questions 24-28 using the information below Regression Statistics Multiple R Obs Quarter Year Sales Sales 1 1 2011 71 0.995 2 2011 49 R Square 0.990 90 3 3 2011 58 Adjusted R Square 0.986 80 4 2011 78 Standard Error 1.561 70 5 1 2012 68 Observations 16 60 2 2012 41 7 3 2012 55 50 ANOVA 8 4 2012 73 40 df 9 2013 62 30 10 2 2013 38 Regression Residual 4 20 11 3 2013 53 11 10 2013 12 4 70 Total 15 0 1 13 2014 59 6 7 8 11 12 13 16 9 10 14 15 14 2014 32 Coefficient 15 3 2014 50 Sales Intercept 81.75 16 2014 65 S1 9.575 17 1 2015 S2 -33.55 18 2015 19 2015 S3 -18.525 20 4 2015 Time 1.025 Using the model, predict sales for the third quarter of 2014. 65.35 66.37 47.85 50 None of the above Nm no

Answer 1

(first part) right choice is 9.

here number of observations=n=12

period of moving average=k=3

required answer=n-k=12-3=9

(second part) right choice is. There are 3 dummy variables used to differentiate between 4 seasons effect

(Third part) right choice is 47.85

the model is y^= 81.75-9.575*S1-33.55*S218.525*S3+1.025*Time

for year 2014 and Quarter 3 the

time would be =15 and S1=0, S2=0 and S3=1

y^=81.75-18.525+15*1.025=47.85

answer is 47.85