Chapter 3

Summary : Forecasting


Forecasting helps managers and businesses develop meaningful plans and reduce uncertainty of events in the future. Managers want to match supply with demand; therefore, it is essential for them to forecast how much space they need for supply to each demand.

Two important aspects associated with forecasting are the expected level of demand and the forecast's degree of accuracy. Two general approaches to forecasting are qualitative and quantitative. Also, there are three types of forecasting techniques:
  1. Judgmental forecasts,
  2. Time-series forecasts, and
  3. Associative models.

Judgmental forecasts rely on subjective inputs from various sources. Time-Series forecasts projects patterns identified in recent time-series observations. A time-series is a time-ordered sequence of observations taken at regular time intervals. Associative models are based on the development of an equation that summarizes the effects of predictor variables. Predictor variables are used to predict values of the variable of our interest.

It is important to know how to calculate a forecast error: Error = Actual - Forecast. There are three ways of measuring the accuracy of forecasts: MAD, MSE, and MAPE. MAD weighs all errors evenly. MSE weighs errors according to their squared values. Lastly, MAPE weighs according to relative error.

Qualitative forecasting is subjective, while quantitative forecasting involves projecting historical data, or developing associative models. Judgmental forecasts are qualitative, while time-series forecasts and associative models are both quantitative. Quantitative forecasting methods include the Naïve forecasting method, the moving average method, the weighted average method, and the exponential smoothing method. Forecasts are never 100% accurate; hence, there is always room for improvement.

Chapter 3 introduced different kinds of forecasting techniques; however no single technique works best in every situation. Random variation is always present within forecasts and there will always be a degree of residual error within forecasts. Forecasts are the basis for an organization's schedule, and therefore the accuracy of these forecasts will dictate how many resources must be used, the output production, and the timing of a production schedule.The higher the accuracy the higher the cost, therefore the best forecast is generated from some combination of accuracy and cost. The availability of historical data, computer software, as well as the time needed to gather and analyze data must be taken into consideration when selecting a forecast technique. Computers play an important role in preparing forecasts based on quantitative data.Because forecast error equals the actual value minus the forecast value. Positive errors will occur when the forecast is too low and negative errors will occur when the forecast is too high.

There are a wide variety of forecasting techniques that can broadly be classified in three main approach


  1. Judgmental Forecasts: Useful when forecasts must by done in a short period of time, when data is out dated, unavailable, or there's limited time to collect it.
  2. Time Series Forecasts: Most Common, are used to identify specific patterns in data and use them to project future forecasts
  3. Associative models: identify related variables in order to predict necessary forecasts.

Forecasting is a method used to predict and place all information mainly in design and operating systems. They both estimate what that information will look like in the future. In order to do so, one must determine the purpose, establish a time horizon, select a forecasting technique, make it, and then monitor the new forecast. The methods used to decrease error include: Delphi method, naive method, and weighted average method. A major issue in forecasting is seasonal variations because it has a repeating movement. This is where the control chart becomes important mainly because it monitors forecasting errors.

Chapter Three focuses on forecasting which involves a statement about the future values of a variable of interest. There are three forecast techniques - judgmental, time-series and focus. A proper forecast should meet certain requirements which are timely, accurate, reliable, expressed in meaningful units, in writing, cost effective and finally simple to understand and use. After the forecast has been made, it is important that organizations study them and meet the demands of consumers by reacting to the forecast. However, there is no way to predict things with complete accuracy; we can only choose the best forecasting to fit different situations.

Forecasts—Forecasting Demands
Forecasting is an important part of a business because a forecast results in a more accurate inventory. Main uses for forecasts include: Plan the system (long-range plans) and plan the use of the system (short-range plans). The four common types of forecasts are naive forecasts, moving average, weighted moving average and exponential smoothing.
Having an accurate forecast is very important. Chapter 3 also focuses about forecast error. Error is calculated by subtracting the forecast from the actual error. It’s also important that firms use the most accurate forecasting method. The three most common ways to measure the errors in forecasts are the mean deviation, the mean squared error, and the mean absolute percent error.

Forecasting is a statement pertaining to the future value of a variable of interest. Its crucial for good forecasting to be reliable, cost effective, simple and concise. Its very important for a forecast to be correct and that their be as few errors as possible. Errors greatly effect forecast accuracy and are calculated as Error = Actual - Forecast. If their are too many errors in a forecast, then action is required to correct those errors.There are two main approaches in forecasting. One approach is quantitative forecasting which relies on past variables and data. The other is qualitative forecasting which is more about opinions, fundamental analysis, and intuitions.


SUMMARY - Judgmental Forecasts

This section covers Judgmental forecasts, which are useful when need to make a quick forecast or if historical data is not available.

Judgmental forecasts include executive opinions, sales-force opinions, consumer surveys, and the Delphi method. Executive opinions utilizes a small group of upper-level managers to develop a forecast. Sales-force opinion method uses the sales staff or the customer service staff to make forecasts based on information obtained through direct contact with customers. Consumer surveys are used to gather information directly from customers to generated a forecast.

In Chapter 3, various methods of forecasting methods are explained in detail the function of each forecasting methods and how they are used in everyday situations. These forecast help managers try to predict future events in hopes of improving company's operations. Forecasts are split into two different groups, quantitative and qualitative. Qualitative forecasts are surveys, opinions, and sales-force estimates. The two major quantitative forecasts are analysis of time-series data and associative techniques. Depending on the situation not all forecasts work accurately and some work better than others.


1. Which of the following is NOT a step in the forecasting process? p.g. 74
A. Determining the purpose of the forecast
B. Establishing a time horizon
C. Selecting a forecast technique
D. Creating demand for forecasting
E. Monitoring the forecast
ANSWER D. Create demand for forecasting

2. Forecast accuracy _ as the time period covered by the forecast _ . p.g. 73
A. increases, decreases
B. decreases, increases
C. is eliminated continues
D. continues is eliminated
E. none of the above
ANSWER B. decreases, increases

3. Good forecasting requires which of the following element(s)? p.g. 74
A. timely
B. accurate
C. reliable
D. cost-effective
E. All of the above
ANSWER E. All of the above

4. The mean absolute deviation (MAD) is the _ way to compute _, as weighted errors computes _ . p.g. 77
A. hardest, linearly
B. easiest, linearly
C. error, linearly
D. squared error, linearly
E. none of the above
ANSWER B. easiest, linearly

5. The Forecast Error equation is: p.g. 75
A. Error=Actual-Forecast
B. Error=Forecast-Actual
C. Error=(Actual-Forecast)^2
D. Error=(Actual-Forecast)/n
E. None of the above
ANSWER A. Error=Actual-Forecast

1- What are forecast values used for?:
a) plan the system
b) plan the use of the system
c) provide future goals
d) all of the above
e) none of the above

ANSWER: D page 79

5- A manager is trying to calculate the forecasting error for five periods, he successfully calculated the sum of the squared errors to be 39. What is the forecasting error using MSE?
a) 2.6
b) 9.75
c) 7.8
d) 6.85
e) 10

ANSWER B page 76

1. Forecast Error is equal to
a) the forecast value - the actual value
b) the actual value - the forecast value
c) the absolute value - the forecast value
d) the forecast value - the absolute value
e) the absolute value - the value
ANSWER: B page 75

2. When making periodic forecasts, it is important to
a) make sure the the actual value exceeds the forecast value
b) make sure the forecast value exceeds the actual value
c) make sure the the errors are within reasonable bounds
d) make sure the forecast value is outside a reasonable bound
e) take corrective actions.
ANSWER: C found on pg 75

3. Positive Forecast Errors occur when
a) the forecast is too high
b) the forecast is too low
c) the forecast equals the actual value
d) the actual value exceeds the forecast value
e) none of the above
ANSWER: B page 75

4. Negative Forecast Errors occur when
a) the forecast equals the actual value
b) the forecast is too low
c) the actual value exceeds the forecast value
d) the forecast is too high
e) the value equals actual value
ANSWER: D page 75

5. Which of the following is a way forecast errors influence decision making
a) They determine the success or failure of the chosen forecasting alternative
b) They determine at which level the actual value should exceed the forecast value
c) They determine at which level the forecast value should exceed the actual value
d) They do not affect decision making: forecast error is too random a variation to be accounted for
e) They determine how to summarize forecast error over time
ANSWER: A found on page 75




1. A data series that shows a short-term regular variation related to the calender or time of day:
a) trend
b) seasonality
c) cycle
d) irregular variation
e) random variation
ANSWER: B
P.79

2. Which forecasting would be best if the forecast horizon was short - medium, preparation time was short - medium, and personal background had little sophistication?
a) moving average
b) trend model
c) seasonal
d) simple exponential smoothing
e) all the same

ANSWER: C
P. 104

3. Given the following data, the error is?
Forecasted Sales- 110 & Actual Sales- 130
a) -20
b) 20
c) 240
d) 0
e) none of the above

ANSWER: B
P. 75

4. What is the first step in the forecasting process?
a) establish a time horizon
b) select a forecasting technique
c) obtain data
d) determine the purpose of the forecast
e) none of the above

ANSWER: D
P. 74

5. The two most important factors when choosing a forecasting method are?
a) cost and accuracy
b) cost and time
c) time and accuracy
d) quality and time

ANSWER: A
P. 103


6.) When are forecasts made?
a.) Weekly
b.) Monthly
c.) Quarterly
d.) Annually
e.) All of the above
ANSWER: E.
P. 99


1. The actual demand was 50 units while the forecast value was 30 units. What is the error?
A. 15
B. 20
C. 25
D. 10
E. There is no error.
Answer: B, page 75

2. Which one of these is a wave-like variation lasting more than a year?

A. Cycle
B. Seasonal
C. Cycle
D. Irregular
E. Random
Answer: A, page 79

3. Which of these forecasts equals the previous period’s actual value?
A. MAD
B. MSE
C. MAPE
D. Naive
E. None of the above
Answer: D, page 80

4. Which one of these is a time series forecast?
A. Trend
B. Seasonality
C. Cycle
D. Random Variation
E. All of the above
Answer: E, page 79

5. The previous forecast was 100 units. The actual forecast was 150 units. There is an alpha of .5. What is the next forecast going to be?
A. 100
B. 150
C. 125
D. 200
E. 175
Answer: C, pages 83-84


Murtaza Valika
mvalik2



1. What type of relationship is there between accuracy and the forecast horizon.
a) Positive
b) Inverse
c) Zero
d) Exponential
e) Parabolic
Answer: B (pg. 73)

2. Looking at the historical data, there are two peaks and troughs that can be seen. There is a medium forecast horizon and moderate preparation time. Which forecasting method should be selected?
a) Moving average
b) Causal regression models
c) Seasonal
d) Exponential smoothing
e) Naive forecasting
Answer: C (pg. 79)

3. A proactive approach to a forecast:
a) Seeks to actively influence demand
b) Requires a subjective assessment of the influence on demand
c) May need two forecasts
d) All of the above
e) None of the above
Answer: D (pg. 105)

4. Simple exponential smoothing is appropriate when data:
a) Exhibits a linear trend
b) Varies around an average or has gradual changes
c) Has regularly repeating upward or downward movements
d) Exhibits no clear pattern
e) Exhibits irregular behavior
Answer: B (pg. 83-85 )

5. What is the naive forecast in the stable series using the following information: Previous Actual Value = 34, Previous Forecast Value = 30.
a) 34
b) 30
c) 4
d) 32
e) 33
Answer: A (pg. 79)

6. Monitoring the forecast is important because:
a) Forecasts errors almost certain- there is always room for improvement
b) It is important to determine whether the forecasts are performing satisfactorily
c) The model may be outdated
d) All of the above
e) None of the above
Answer: D (pg. 99)

Judy Chen
JChen60


1. When period 1 has a sale of 10 units, what is the forecast for the sales in the next period using the naive methods?
a) 8 units
b) 9 units
c) 10 units
d) 10.5 units
e) 12 units
Answer is c. page 79

2. Which of the following is considered an input for judgmental forecast?
a) Executive opinions
b) Salesforce opinions
c) Consumer surveys
d) Delphi method
e) All of the above
Answer is e. page 77

3. Which of the following is not an element of a good forecast?
a) The forecast should be timely.
b) The forecast should be accurate.
c) The forecast should be oral.
d) The forecast should be reliable
e) All of the above
Answer is c. page 74


4. Which of the following are residual variations that remain after all other behaviors have been accounted for?
a) Seasonality
b) Cycle
c) Random Variation
d) Trend
e) None of the above
Answer is c. page 79

5. Naïve Forecast is best used when:
a) The time series is stable
b) There is a trend
c) There is seasonality
d) All of the above
e) None of the above
Answer is d. page 79


Marco Chen
mchen26


Questions:

1. Which forecasting method uses subjective inputs such as opinions from consumer surveys, sales staff, managers, executives, and experts?
A) Judgmental forecasts
B) Time-series forecasts
C) Associative models
D) All of the Above
E) None of the above
Answer: A , pg. 77

2. Which forecasting method has the advantage of bringing together the knowledge and talent of various managers, but runs the risk that the view of one person may prevail?
A) Salesforce opinions
B) Consumer surveys
C) Delphi method
D) Executive opinions
E) Associative models
Answer: D, pg 77

3. Which forecasting method is the most useful for assessing changes in technology and their impact on an organization?
A) Salesforce opinions
B) Executive opinions
C) Delphi method
D) Consumer surveys
E) Time-series forecasts
Answer: C, pg 78

4. In which forecasting method may the persons offering their opinion be overly optimistic/pessimistic and thus may be unable to distinguish between what customers would like to do and what they actually will do?
A) Consumer surveys
B) Salesforce opinions
C) Delphi method
D) Executive opinions
E) Judgmental forecasts
Answer: B, pg 78

5. What forecasting method(s) utilizes qualitative techniques rather than quantitative techniques?
A) Judgmental forecasts
B) Time-series forecasts
C) Associative models
D) A and B
E) All of the above
Answer: A, pg 77

Rahul Singh
rsingh24


1. What is the forecast for period 4 if period 1 = 65, 2= 54, 3=88.( using naive method)

a) 65
b)88
c)54
d)11
e)23
Answer: B page 79

2. Which one refers to short-term regular variations?

a) Trend
b) Cycles
c) Irregular variations
d) Random variations
e) seasonality
Answer: E page 79

3. Which one of these uses historical data for forecasting?

a) Associative models
b) Time-series forecasts
c) Judgmental forecasts
d) Consumer Surveys
e) Delphi Method
Answer: B page 77-81



this question is a duplicate
4. Which is the element of a good forecast?

a) timely
b) accurate
c) reliable
d) cost-effective
e) all of the above
Answer: E need page number

5. What is the error when the actual is 333 and the forecast is 340?

a) 7
b) -7
c) 14
d) -14
e) 20
Answer: B page 75

Kwok On Leung
kleung7


Need to have five option and page numbers
1. Forecasts based on judgment and opinion include which of the following:

a) Executive opinions
b) Salesforce opinions
c) Consumer Surveys
d) Opinions of experts
e) All the above
Answer E
p.g. 77

2. The two general approaches to forecasting are:

a) Quantitative and Qualitative
b) Qualitative and data analysis
c) Qualitative and judgmental
d) Associative and Historical
e) None of the above
Answer A
p.g. 77

3. Analysis of time-series data uses data to predict future data:

a) Predictable
b) Historical
c) Future
d) Current
e) Random
Answer B
p.g. 77

4. The mean absolute deviation of 1, -2, -3 and 2 is

a) 4
b) 9
c) 2
d) 1
e) 5
Answer C need page number

5. Two factors in deciding which forecast to chose are

a) Cost and accuracy
b) Reliability and accuracy
c) Cost and Reliability
d) Reliability and validity
e) None of the above

Answer A

Michael Hare: Mhare2

Chapter 3


Questions NEED FIVE OPTIONS FOR EACH QUESTION
1. (True/False) Forecast accuracy decreases as the time horizon increases
True! Since short-range forecasts tend to have fewer uncertainties they’re usually more accurate. p. 73

2. Which method of detecting forecast errors is the most effective?
a) Mean deviation
b) Mean squared error
c) Mean absolute percent error
d) Depends on the situation
e) None of the Above

d) Depends on the situation p.75-77

3. Compute a three-period moving average.

Period
Demand
1
57
2
50
3
54
4
52
5
56

a) 53
b) 54
c) 55
d) 56
e) Cannot be determined


b) 54 p. 81

4. What is a process in which managers and staff complete a series of questionnaires to achieve a forecast?

a) Seasonal relative
b) Tracking signal
c) Delphi method
d) Qualitative assessment
e) Both c and b

c) Delphi method p. 78

5. What is one way to attempt to detect biases in errors over time?

a) Judgmental forecasts
b) Tracking signal
c) Associative models
d) Predictor variable
e) Error Forcasting

b) Tracking signal p.101


Eden Temple
etempl2


1) Quantitative techniques consist mainly of
a. Hunches of managers
b. hard data
c. opinions of outside consultants
d. both a and b
e. none of the above
Answer: b
p.g. 77

2) What happens when errors go far beyond “acceptable” limits.
a. corrective action is needed
b. nothing is done because nothing can be done
c. a forecast can not be complete
d. no forecast ever goes beyond “acceptable” limits
e. none of the above
Answer: a
page 75

3) After determining the purpose of a forecast what is the next step in the forecasting process?
a. Making the forecasting
b. getting opinions of what the forecast should look like
c. looking into past forecasts
d. establishing a time horizon
e. writing a report of what is to be included in the forecast

Answer: d
p.g. 74

4) A good forecast will be
a. reliable
b. accurate
c. simple
d. cost effective
e. all of the above
Answer: e
p.g. 74

5) What does it mean when there is seasonality, a trend, or the time series is stable?
a. a forecast can not be done
b. a naïve forecast can be used
c. accuracy will be very good
d. their will be many errors
e. this means absolutely nothing
Answer: b
p.g. 79

Miguel Guzman
mguzma4




1. What is a forecasting technique that uses explanatory variables to predict future demand?
A. Time-series forecasts
B. Judgmental forecasts
C. Associative models
D. Delphi method
E. Naive method

C. Associative method. P 77

2. Variables that can be used to predict values of the variables of interest are
A. Random variations
B. Errors
C. Seasonal variations
D. Regression lines
E. Predictor variables

E. Predictor variables. P 94

3. A technique for fitting a line to a set of points is
A. Associative model
B. Correlation
C. Delphi method
D. Regression
E. Exponential smoothing

D. Regression. P 94

4. What minimizes the sum of the squared vertical deviations around the line?
A. Weighted Average
B. Least square line
C. Mean squared error
D. Exponential smoothing
E. Tend-adjusted exponential smoothing

B. Least square line. P 94


5. A measure of the scatter of points around a regression line is
A. Standard error of estimate
B. correlation
C. regression
D. least square line
E. seasonal variation

A. Standard error of estimate. P 96

Klongi2
Krista Longi



5 different answer choices are required
1. Which one of the following is NOT a judgment/opinion forecasting approach?
A. Delphi technique
B. Direct-contact composites
C. Hull technique
D. Consumer surveys
E. Executive opinions
p.g. 77, 78

2. In the Additive model what does demand equal?
A. Trend + Seasonality
B Trend X Seasonality
C. Seasonality - Trend
D. Seasonality + 2(Trend)
E. (Trend + Seasonality)^2
page 90-91

3. Which one of these techniques for averaging was not discussed in Ch. 3 in your textbook?
A. Moving Average
B. Exponential Smoothing
C. Weighted moving Average
D. Boost Average
E. Naive Method
page 79

4. Once you have established a time horizon in the forecasting process what would be the next step?
A. Make a forecast
B. Select a forecasting technique
C. Monitor the forecast
D. Obtain data
E. Determine the purpose of the forecast
page 74

5. What are seasonal variations?
A. Regularly repeated movements in series values that can be tied to recurring events.
B. Regularly repeated movements in series values that cannot be tied to recurring events.
C. When a season like fall changes into winter.
D. When a season like winter changes into fall.
E. None of the above
page 79

Cory J. Renner
crenne3


1) What are the steps in the forecasting process?

A) Make the forecast
B) Determine the purpose of the forecast
C) Establish a time horizon
D) C, B, A
E) B, C, A
Answer: E
Page 70

2) Which of the following is an element of a good forecast?
A) Precise
B) No need to reliable
C) Timely
D) Spoken but not written
E) None of the Above
Answer: C
Page 70

3) What are the approache(s) to a forecast?

A) Prevention
B) Proactive
C) Banzai
D) Reactive
E) A & B
Answer: E
Page: 99

4) Which of the following is most similar to weighted average?

A) Exponential smoothing
B) Moving Average
C) Time Series
D) A & B
E) None of the above
Answer: B
Page 75

5) What does the "b" stand for in the linear trend equation: F = a + bt?

A) Time periods
B) Forecast
C) Value
D) Slope
E) None of the above
Answer: D
Page 79
slwin2

The following table is the historical data for Apple Republic's sales in their clothing up until November, 2009.

Time Period
Demand
August,2009
800
September,2009
675
October,2009
700
November,2009
1100
1) What is the forecast for December, 2009 if we use naive approach?

A) 800
B) 675
C) 700
D) 1100
E) None of the above

Answer: D (p. 79-83)

2) What is the forecast for December, 2009 if we use a three-year weighted moving average with .5, .3, and .2 (with .5 for the most recent month)?

A) 825
B) 895
C) 768
D) 800
E) 900

Answer: B (p. 79-83)