uiz 2 CASE UPS Air Finance Division The Air Finance Division is one of several divisions within United Parcel Service Financial Corporation, a wholly-owned subsidiary of United Parcel Service (UPS). The Air Finance Division has the responsibility of providing financial services to the company as a whole with respect to all jet aircraft acquisitions. In addition, this division provides financing to independent outside entities for aviation purchases as a separate and distinct operation. Historically, the non-UPS financing segment of the Air Finance Division has provided a higher rate of return and greater fee income than the UPS segment however it is more costly to pursue. Funding forecasts for the non-UPS market segment of the Air Finance Division have been highly subjective and not as reliable as the forecasts for other segments. The table below lists 10 years of monthly funding requirements for the non-UPS Air Finance Division segment. These data were collected from management reports during the period from January 1989 through December 1998 and of the month end figures in millions of dollars. The objective in this case study is to develop a time series forecasting model. The year 1998 data is to be reserved as a test set. The forecasting model is to be developed based on the years 1989 to 1997. In Quiz 2, questions 11 - 20 may refer to the UPS data. You are to answer the questions by performing the appropriate analyses in Excel and Minitab. The data will be found in the Excel file UPS_Data. You can copy and paste the data from Excel into Minitab. Quiz 2 CASE UPS Air Finance Division The Air Finance Division is one of several divisions within United Parcel Service Financial Corporation, a wholly-owned subsidiary of United Parcel Service (UPS). The Air Finance Division has the responsibility of providing financial services to the company as a whole with respect to all jet aircraft acquisitions. In addition, this division provides financing to independent outside entities for aviation purchases as a separate and distinct operation. Historically, the non-UPS financing segment of the Air Finance Division has provided a higher rate of return and greater fee income than the UPS segment however it is more costly to pursue. Funding forecasts for the non-UPS market segment of the Air Finance Division have been highly subjective and not as reliable as the forecasts for other segments. The table below lists 10 years of monthly funding requirements for the non-UPS Air Finance Division segment. These data were collected from management reports during the period from January 1989 through December 1998 and of the month end figures in millions of dollars. The objective in this case study is to develop a time series forecasting model. The year 1998 data is to be reserved as a test set. The forecasting model is to be developed based on the years 1989 to 1997. In Quiz 2, questions 11 - 20 may refer to the UPS data. You are to answer the questions by performing the appropriate analyses in Excel and Minitab. The data will be found in the Excel file UPS_Data. You can copy and paste the data from Excel into Minitab. Quiz Note: It is recommended that you save your response as you complete each question. Question 1 (1 point) In multiple regression analysis, residual plots are used to detect Question 1 options: The existence of autocorrelations among error terms in a time series model The existence of multicollinearity among independent variables in a model The existence of interactions between the independent variables in the model The existence of patterns that show that the variance of error terms is not constant Exactly two of the above are true Save Question 2 (1 point) A multiple regression analysis consists of 30 observations and 2 independent variables. The Cook's distance value for a potential outlier will have ___ degrees of freedom in the numerator and ___ degrees of freedom in the denominator. Question 2 options: 3 : 28 2 ; 27 3 ; 27 27 ; 3 None of the above Save Question 3 (1 point) Which of the following statements about a point of leverage is false? Question 3 options: It can exert a major reduction in the value of It is far removed from the average values of the independent variable in a residual plot It can exert a major influence on the slope of a regression line It has a large standardized residual Exactly two of the above statements are false Save Question 4 (1 point) A statistician is analyzing a data set consisting of one observation every month for a period of three years. A time series model is constructed with two predictor variables Question 4 options: If the data set exhibits significant positive serial correlation we would expect the Durbin-Watson greater than 2. The statistician will conclude there is negative Lag 1 serial correlation at the 1% level of significa statistic exceeds 2.79 The statistician will conclude there is negative Lag 1 serial correlation at the 1% level of significa statistic exceeds 2.85 A Dubin-Watson statistic in excess of 4 is a sure sign of serial correlation None of the above Save Question 5 (1 point) The CEO of a large Canadian chain of department stores believes that her stores' total sales have been showing a linear trend since 1980. She uses Microsoft Excel to obtain the partial output below. The dependent variable is sales (in millions of dollars), while the independent variable is coded years, where 1980 is coded as 0, 1981 is coded as 1, etc. the forecast for sales in 1998 is Question 5 options: 44.46 45.24 46.02 14.04 None of the above Save Question 6 (1 point) When testing for normality we conclude that the distribution is approximately normal if Question 6 options: The Anderson-Darling statistic has a p-value > .05 A normal probability plot is bell-shaped in appearance about 95% of standardized residuals are greater than 2 A plot of residuals against fitted values is approximately linear None of the above Save Question 7 (1 point) If unemployment in August actually decreases, but the seasonally adjusted value shows an increase, then the seasonal index for August Question 7 options: is greater than July's is less than July's cannot be compared to July's is equal to July's none of the above Save Question 8 (1 point) A time series records quarterly sales in millions of dollars of a product starting in the winter (first quarter) of 2010. Using regression software the trend component of this series is given by T = 1370.02 + 2.8t. The medians of the ratio-to-moving average values for the four quarters have been calculated to be 0.75, 1.12, 1.15, and 0.66 for the first, second, third, and fourth quarters, respectively. A trend-seasonal forecast for the third quarter of 2015 is closest to: Question 8 options: 1646 million 1793 million 1434.9 million 1789 million none of the above Save Question 9 (1 point) To assess the adequacy of a time series forecasting model, a measure that is often used is Question 9 options: Mean Error Absolute value of mean error Mean value of absolute errors Square root of absolute error values Two of the above are correct Save Question 10 (1 point) The ratio of a particular month's actual sales value to the corresponding 12 month centered moving average measures the effect of Question 10 options: seasonal variation only combined seasonal and random effects Combined trend and cyclical effects Combined trend, cyclical, and random effects None of the above Save Question 11 (1 point) A time series plot of the UPS data is Question 11 options: stationary Non-stationary in the mean Non-stationary in the variance Non-stationary in both the mean and the variance none of the above Save Question 12 (1 point) A time series plot of the UPS data exhibits: Question 12 options: trend but not seasonality seasonality but not trend both trend and seasonality extreme heteroscedasticity none of the above Save Question 13 (1 point) Create a new worksheet containing the first 9 years of data (1989 - 1997). We will call this the reduced data set. The following questions (Q14 - Q16) pertain to the reduced data set. Assume a multiplicative decomposition model and use the Time Series Decomposition menu. Using this model the fitted trend equation for the UPS production data is Question 13 options: Tt = 20.793 + .06365t Tt = 21.169 + .05402t Tt = 20.793 + .05402t Tt = 21.169 + .06365t none of the above Save Question 14 (1 point) Using the Time Series Decomposition menu, we would conclude that UPS funding for July is Question 14 options: 13% above average 10% above average Approximately average Cannot tell none of the above Save Question 15 (1 point) Obtain a sales forecast for February 1998 using trend and seasonal components. Answer to 2 decimal places. Question 15 options: 29.92 23.33 24.29 24.83 None of the above Save Question 16 (1 point) Using Minitab, create forecasts for 1998 and use the test set to calculate the MAPE for the forecast. The MAPE is closest to: Question 16 options: 27.3% 5.3% 2.3% 7.8% None of the above Save Question 17 (1 point) Based on the ACF and PACF of D1D12 which of the following ARIMA models would be appropriate? Question 17 options: ARIMA(1,0,1)(1,0,1)12 ARIMA(0,0,1)(0,0,1)12 ARIMA(0,1,1)(0,1,1)12 ARIMA(0,1,0)(0,0,1)12 Two of the above Save Question 18 (1 point) Use Minitab to obtain forecasts based on the reduced data set for UPS for 1998 using the ARIMA model ARIMA(0,1,0)(0,1,1)12. The forecast for August 1998 is Question 18 options: 29.71 26.62 32.52 30.41 None of the above Save Question 19 (1 point) For the forecasts for 1998 from the ARIMA(0,1,0)(0,1,1) 12 model the MAPE, expressed as a percentage is Question 19 options: 6.2% 5.2% 15.1% 0.52% None of the above Save Question 20 (1 point) Your recommendation of a forecasting model to the UPS should be Question 20 options: The Multiplicative Decomposition Model The ARIMA(0,1,0)(0,1,1)12 Model Both models because they are equally good at forecasting Neither model because they ignore seasonal variation None of the above Save Year 1989 1990 1991 1992 Month Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov UPS 16.2 16.7 18.7 18.8 20.6 22.5 23.3 23.8 22.3 22.3 22.1 23.6 20.1 21.6 21.6 21.9 23.4 25.9 26.0 26.2 24.7 23.5 23.4 23.9 20.0 20.4 20.9 21.6 23.2 25.6 26.6 26.3 23.7 22.2 22.7 23.6 20.2 21.1 21.5 22.2 23.4 25.7 26.3 26.2 23.6 22.8 22.8 1993 1994 1995 1996 Dec Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov 23.3 21.0 21.7 22.2 23.1 24.8 26.6 27.4 27.1 25.3 23.6 23.5 24.7 21.2 22.5 22.7 23.6 25.1 27.6 28.2 27.7 25.7 24.3 23.7 24.9 21.8 21.9 23.1 23.2 24.2 27.2 28.0 27.6 25.2 24.1 23.6 24.1 20.7 22.0 22.5 23.6 25.2 27.6 28.2 28.0 26.3 25.9 25.9 1997 1998 Dec Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec 27.1 22.9 23.8 24.8 25.4 27.0 29.9 31.2 30.7 28.9 28.3 28.0 29.1 25.6 26.5 27.2 27.9 29.4 31.8 32.7 32.4 30.4 29.5 29.3 30.3