QUESTION 1

1. When discussing the Delphi procedure, Rowe and Wright suggest a number of guidelines that include

		using homogenous experts.
		weighting of the experts' estimates.
		unframed questions.
		using more than 20 people.
		None of the options are correct.

QUESTION 2

1. A large sample of X-Y data values are analyzed and reveal a correlation coefficient of .88. Which statement is correct?

		A fairly strong negative linear relationship exists.
		If r had been +.88, the correlation would have been much stronger.
		The correlation is weak because r is less than -1.
		A weak negative relationship exists.

QUESTION 3

1. "Event Models" as used in ForecastX

		are a type of growth model.
		are a form of exponential smoothing.
		are a type of simple regression.
		are a type of moving average.

QUESTION 4

1. A simple-centered 3-point moving average of the time-series variable Xt is given by:

		(Xt+Xt-1+ Xt-2)/3.
		(Xt-1+Xt-2+ Xt-3)/3.
		(Xt+1+Xt+ Xt-1)/3.
		None of the options are correct.

QUESTION 5

1. Consider the calculation of Root Mean Square Error (RMSE) used as a measure of forecast fit. RMSE applied to the analysis of model forecast errors, treats

		large and small forecast errors unequally on the margin.
		levels of large and small forecast errors equally.
		every forecast error with the same penalty.
		large and small forecast errors equally on the margin.

QUESTION 6

Date	Total Houses Sold (000) THS	Nave Forecast (-12) THSF	Error	Squared Error
Jan-03	76
Feb-03	82
Mar-03	98
Apr-03	91
May-03	101
Jun-03	107
Jul-03	99
Aug-03	105
Sep-03	90
Oct-03	88
Nov-03	76
Dec-03	75
Jan-04	89	76	13	169
Feb-04	102	82	20	400
Mar-04	123	98	25	625	MSE = 155.83
Apr-04	109	91	18	324
May-04	115	101	14	196	RMSE = 12.48
Jun-04	105	107	-2	4
Jul-04	96	99	-3	9
Aug-04	102	105	-3	9
Sep-04	94	90	4	16
Oct-04	98	88	10	100
Nov-04	79	76	3	9
Dec-04	72	75	-3	9
Jan-05		89
Feb-05		102
Mar-05		123
Apr-05		109
May-05		115
Jun-05		105
Jul-05		96
Aug-05		102
Sep-05		94
Oct-05		98
Nov-05		79
Dec-05		72

1. In the table above, Total Houses Sold in the United States are forecasted by what method?

		A nave model
		A modified nave model with a lag of 4
		A modified nave model with a lag of 12
		A simple smoothing model

QUESTION 7

1. "Index 1" in the GAP results must refer to what time period?

		The first quarter of the year
		The second quarter of the year
		The third quarter of the year
		The fourth quarter of the year

QUESTION 8

ate	Total Houses Sold (000) THS
Jan-03	76
Feb-03	82
Mar-03	98
Apr-03	91
May-03	101
Jun-03	107
Jul-03	99
Aug-03	105
Sep-03	90
Oct-03	88
Nov-03	76
Dec-03	75
Jan-04	89
Feb-04	102
Mar-04	123
Apr-04	109
May-04	115
Jun-04	105
Jul-04	96
Aug-04	102
Sep-04	94
Oct-04	98
Nov-04	79
Dec-04	72

1. The data above represents the total houses sold in thousands of units per month through December of 2004. Use an appropriate nave model to forecast January 2005 sales.

		76
		89
		80
		72
		94

QUESTION 9

1. A "product life cycle" includes what different stages?

		Decline
		Growth
		Maturity
		Introduction
		All of the options are correct.

QUESTION 10

1. What values of Theil's U statistic are indicative of an improvement in forecast accuracy relative to the no-change nave model?

		U = 0
		U < 0
		U > 1
		U < 1
		None of the options are correct.

QUESTION 11

1. A random sample of bolts is taken from inventory, and their lengths are measured. The average length in the sample is 5.3 inches with a standard deviation of .2 inches. The sample size was 50. The point estimate for the mean length of all bolts in inventory is

		.2 inches.
		5.3 inches plus or minus .2
		4.908 to 5.692 inches.
		5.3 inches.

QUESTION 12

1. Which of the following points about supply chain management is incorrect?

		If you get the forecast right, you have the potential to get everything else right in the supply chain.
		Forecasts of sales are required for partners in the supply chain.
		Forecasts are required at each step in the supply chain.
		Collaborative forecasting systems across the supply chain are needed.
		None of the options are incorrect.

QUESTION 13

1. Which subjective sales forecasting method may have the most information about the spending plans of customers for a specific firm?

		Index of consumer sentiment
		Delphi Method
		Sales Force Composites
		Jury of Executive Opinion
		None of the options are correct.

QUESTION 14

1. A difference between the population standard deviation of the random variable X and the standard deviation of the sampling distribution of the sample mean is

		application to the t distribution.
		one is based upon the other.
		the possibility of sampling error.
		dependence on sample size.
		All of the options are correct.

QUESTION 15

1. Growth

Audit Trail - Statistics
Accuracy Measures	Value
AIC	66.28
BIC	66.07
Mean Absolute Percentage Error (MAPE)	39.37	%
R-Square	99.78	%
Adjusted R-Square	99.57	%
Root Mean Square Error	15.55
Method Statistics	Value
Method Selected	Gompertz Curve
Minimum	0.00
Maximum	1,200.00

1. In the growth model Audit Trail shown above, a Gompertz Curve was probably selected because

		a "bell shaped" function was expected.
		it was easier to achieve constant improvement as the maximum value was approached.
		the trend was nonlinear.
		it was harder to achieve constant improvement as the maximum value was approached.

QUESTION 16

1. For which data frequency is seasonality not a problem?

		Daily.
		Annual.
		Quarterly.
		Monthly.
		Weekly.

QUESTION 17

1. Thet-Distribution (also called the Student'st-Distribution)

		resembles a Chi-Square distribution.
		resembles a normal distribution.
		resembles both a normal and a Gaussian distribution.
		resembles a Gaussian distribution.
		resembles Theil's Distribution.

QUESTION 18

1. If two large random samples are drawn from two populations, each having a mean of $100, the relevant sampling distribution of their difference has a mean of

		the difference between the two sample means.
		the sum of the two sample means.
		$200.
		0.

QUESTION 19

1. The correlation coefficient () is an extremely important descriptive statistic because

		It provides the forecaster with a diagnostic tool of when regression analysis is appropriate for the business-forecasting problem.
		It provides a measure of the linear association between a pair of random variables.
		It provides a unit-free measure of how two random variables move together.
		All of the options are correct.

QUESTION 20

1. A sample of 100 are selected at random from a process with a mean of 500.52 and a standard deviation of 4.0. Estimate the probability that a sample of 100 would have a mean equal to or greater than 500.52 if the true population mean is really 500.0.

		about .0968.
		about .9032.
		about .4032.
		about .4938.