OPMA 3306 Chapter 3 (Forecasting)

¡Supera tus tareas y exámenes ahora con Quizwiz!

Which of the following forecasting methods is very dependent on selection of the right individuals who will judgmentally be used to actually generate the forecast? A. Time series analysis B. Simple moving average C. Weighted moving average D. Delphi method E. Panel consensus

D. Delphi method

In business forecasting, what is usually considered a short-term time period? A. Four weeks or less B. More than three months C. Six months or more D. Less than three months E. One year

D. Less than three months

In general, which forecasting time frame best identifies seasonal effects? A. Short-term forecasts B. Quick-time forecasts C. Long range forecasts D. Medium term forecasts E. Rapid change forecasts

D. Medium term forecasts

In most cases, demand for products or services can be broken down into several components. Which of the following is not considered a component of demand? A. Average demand for a period B. A trend C. Seasonal elements D. Past data E. Autocorrelation

D. Past data

Measures of error

- Mean absolute deviation (MAD) - Mean absolute percent error (MAPE) - Tracking signal (TS) - Standard error of the estimate Sxy

Smoothing constant must be given a value between

0 and 1

Linear regression

10 to 20 observations. Stationary, trend, and seasonality. Short to medium.

Trend and seasonal models

2 to 3 observations per season. Stationary, trend and seasonality. Short to medium

Medium Term Forecasting

3 months to 2 years

Exponential smoothing with trend

5 to 10 observations needed to start. Stationary and trend. Short.

Weighted moving average and simple exponential smoothing

5 to 10 observations needed to start. Stationary. Short.

Simple Moving Average

6 to 12 months; weekly data are often used. Stationary (i.e. no trend or seasonality). Short.

Short-terms forcasting in business last

< 3 months

long term forecasting

> 2 years

Moving average

A forecast based on average past demand

Simple moving average

A forecast based on past demand. Caculate average demand over most recent period.

Weighted moving average

A forecast made with past data where more recent data are given more significance than older data

Weighted moving average

A forecast made with past data where more recent data are given more significane than older data

Linear regression forecasting

A forecasting technique that assumes that past data and future projections fall around a straight line

linear regression forecasting

A forecasting technique that assumes that the past data and future projections fall around a straight line

Tracking signal

A measure that indicates whether the forecast average is keeping pace with any genuine upward or downward changes in demand

Seasonal

A period of the year characterized by some particular activities

Exponential smoothing

A time series forecasting technique in which each increment of past demand data is decreased by 1-a(alpha)

Exponential smoothing

A time series forecasting technique in which each increment of the past demand data is decrease by (1 -n)

Trend, seasonal, cyclical, autocorrelation, and random

A time series may contain one or more elements:

Time and series analysis

A type of forecast in which data relating to past demand are used to predict future demand

Time series analysis

A type of forecast in which data relating to past demand are used to predict future demand

Collaborative planning. forecasting, and replenishment (CPFR)

A web-based process used to coordinate the efforts of a supply chain Demand forecasting Production and purchasing Inventory replenishment Integrates all members of a supply chain - manufacturers, distributors, and retailers Depends upon the exchange of internal information to provide a more reliable view of demand

Exponential smoothing

A weighted average method which includes all past data in the forecasting calculation. More recent results are weighted more heavily. The most used of all forecasting techniques. An integral part of computerized forecasting.

If you were selecting from a variety of forecasting models based on MAD, which of the following MAD values from the same data would reflect the most accurate model? A. 0.2 B. 0.8 C. 1.0 D. 10.0 E. 100.0

A. 0.2 Mean absolute percent error (MAPE) gauges the error relative to the average demand. For example, if the MAD is 10 units and average demand is 20 units, the error is large and significant, but relatively insignificant on an average demand of 1,000 units. Since the same data is being used in the question, MAPE would be least when MAD was smallest. Therefore A is the correct answer.

If a firm produced a standard item with relatively stable demand, the smoothing constant alpha (reaction rate to differences) used in an exponential smoothing forecasting model would tend to be in which of the following ranges? A. 5 % to 10 % B. 20 % to 50 % C. 20 % to 80 % D. 60 % to 120 % E. 90 % to 100 %

A. 5 % to 10 %

You are using an exponential smoothing model for forecasting. The running sum of the forecast error statistics (RSFE) are calculated each time a forecast is generated. You find the last RSFE to be 34. Originally the forecasting model used was selected because it's relatively low MAD of 0.4. To determine when it is time to re-evaluate the usefulness of the exponential smoothing model you compute tracking signals. Which of the following is the resulting tracking signal? A. 85 B. 60 C. 13.6 D. 12.9 E. 8

A. 85 Tracking Signal = RSFE/MAD = 34/0.4 = 85.

In most cases, demand for products or services can be broken into several components. Which of the following is considered a component of demand? A. Cyclical elements B. Future demand C. Past demand D. Inconsistent demand E. Level demand

A. Cyclical elements

Which of the following is a possible source of bias error in forecasting? A. Failing to include the right variables B. Using the wrong forecasting method C. Employing less sophisticated analysts than necessary D. Using incorrect data E. Using standard deviation rather than MAD

A. Failing to include the right variables

In general, which forecasting time frame compensates most effectively for random variation and short term changes? A. Short-term forecasts B. Quick-time forecasts C. Long range forecasts D. Medium term forecasts E. Rapid change forecasts

A. Short-term forecasts

Which of the following forecasting methods can be used for short-term forecasting? A. Simple exponential smoothing B. Delphi technique C. Market research D. Hoskins-Hamilton smoothing E. Serial regression

A. Simple exponential smoothing

Which of the following forecasting methodologies is considered a time series forecasting technique? A. Simple moving average B. Market research C. Leading indicators D. Historical analogy E. Simulation

A. Simple moving average

A company has a MAD of 10. Its wants to have a 99.7 percent control limits on its forecasting system. It's most recent tracking signal value is 3.1. What can the company conclude from this information? A. The forecasting model is operating acceptably B. The forecasting model is out of control and needs to be corrected C. The MAD value is incorrect D. The upper control value is less than 20 E. It is using an inappropriate forecasting methodology

A. The forecasting model is operating acceptably Tracking Signal = RSFE/MAD hence, 3.1 = RSFE/10 or RSFE =3.1 x 10 = 31. MAD = 10, SD = 1.25 x MAD = 12.5. Since 99.7 percent corresponds to 3 standard deviations from the mean, RSFE would have to be higher than 3 x 12.5 or 37.5 for the forecasting model to be out of control.

The exponential smoothing method requires which of the following data to forecast the future? A. The most recent forecast B. Precise actual demand for the past several years C. The value of the smoothing constant delta D. Overall industry demand data E. Tracking values

A. The most recent forecast

At−1

Actual demand prior period

the main disadvantage in calculating the moving average

All elements must be carried as data because a new forcast period involves adding the new data and dropping the earliest data

true

All forecasts contain some level of error. true or false?

The smoothing constant delta

An additional parameter used in an exponential smoothing equation that include the adjustment for trend

Smoothing constant delta

An additional parameter used in an exponential smoothing equation that includes an adjustment for trend

Collaborative planning, forecasting, and replenishment (CPFR)

An internet tool to coordinate forecasting, production, and purchasing in a firm's supply chain

Components of Demand

Average demand for period time, Trend, Seasonal element, cyclical element, Random variation, Autocorrelation

Given a prior forecast demand value of 1,100, a related actual demand value of 1,000, and a smoothing constant alpha of 0.3, what is the exponential smoothing forecast value? A. 1,000 B. 1,030 C. 1,070 D. 1,130 E. 970

B. 1,030 Forecast = 1,100 + 0.3 x (1,100-1,000) = 1,030

A company wants to forecast demand using the weighted moving average. If the company uses two prior yearly sales values (i.e., year 2012 = 110 and year 2013 = 130), and we want to weight year 2012 at 10% and year 2013 at 90%, which of the following is the weighted moving average forecast for year 2014? A. 120 B. 128 C. 133 D. 138 E. 142

B. 128 Forecast for 2014 = (110x0.1) + (130x0.9) = 11 + 117 = 128

Given a prior forecast demand value of 230, a related actual demand value of 250, and a smoothing constant alpha of 0.1, what is the exponential smoothing forecast value for the following period? A. 230 B. 232 C. 238 D. 248 E. 250

B. 232 Forecast = 230 + 0.1 x (250-230) = 232

A company hires you to develop a linear regression forecasting model. Based on the company's historical sales information, you determine the intercept value of the model to be 1,200. You also find the slope value is minus 50. If after developing the model you are given a value of X = 10, which of the following is the resulting forecast value using this model? A. - 1,800 B. 700 C. 1,230 D. 1,150 E. 12,000

B. 700 The linear regression line is of the form Y = a + bX, where Y is the value of the dependent variable that we are solving for, a is the Y intercept, b is the slope, and X is the independent variable. Hence, Y = 1,200 + (-50) x 10 = 700.

Which of the following is the portion of observations you would expect to see lying within a plus or minus 2 MAD range? A. 57.04 B. 89.04 C. 98.33 D. 99.86 E. 100.00

B. 89.04

Heavy sales of umbrellas during a rain storm is an example of which of the following? A. A trend B. A causal relationship C. A statistical correlation D. A coincidence E. A fad

B. A causal relationship

In most cases, demand for products or services can be broken into several components. Which of the following is considered a component of demand? A. Forecast error B. Autocorrelation C. Previous demand D. Consistent demand E. Repeat demand

B. Autocorrelation

Which of the following forecasting methodologies is considered a qualitative forecasting technique? A. Simple moving average B. Market research C. Linear regression D. Exponential smoothing E. Multiple regression

B. Market research

Which of the following considerations is not a factor in deciding which forecasting model a firm should choose? A. Time horizon to forecast B. Product C. Accuracy required D. Data availability E. Analyst availability

B. Product

In business forecasting, what is usually considered a medium-term time period? A. Six weeks to one year B. Three months to two years C. One to five years D. One to six months E. Six months to six years

B. Three months to two years

f the intercept value of a linear regression model is 40, the slope value is 40, and the value of X is 40, which of the following is the resulting forecast value using this model? A. 120 B. 1,600 C. 1,640 D. 2,200 E. 64,000

C. 1,640 The linear regression line is of the form Y = a + bX, where Y is the value of the dependent variable that we are solving for, a is the Y intercept, b is the slope, and X is the independent variable. Hence, Y = 40 + 40 x 40 = 1,640.

A company wants to generate a forecast for unit demand for year 2014 using exponential smoothing. The actual demand in year 2013 was 120. The forecast demand in year 2013 was 110. Using this data and a smoothing constant alpha of 0.1, which of the following is the resulting year 2014 forecast value? A. 100 B. 110 C. 111 D. 114 E. 120

C. 111 Forecast = 110 + 0.1 x (120-110) = 111

A company wants to forecast demand using the simple moving average. If the company uses four prior yearly sales values (i.e., year 2010 = 100, year 2011 = 120, year 2012 = 140, and year 2013 = 210), which of the following is the simple moving average forecast for year 2014? A. 100.5 B. 140.0 C. 142.5 D. 145.5 E. 155.0

C. 142.5 Forecast for 2014 = (100+120+140+210)/4 = 570/4 = 142.5

A company has actual unit demand for three consecutive years of 124, 126, and 135. The respective forecasts for the same three years are 120, 120, and 130. Which of the following is the resulting MAD value that can be computed from this data? A. 1 B. 3 C. 5 D. 15 E. 123

C. 5 MAD = ABS((124-120)+(126-120)+(135-130))/3 = 15/3 =5

As a consultant you have been asked to generate a unit demand forecast for a product for year 2014 using exponential smoothing. The actual demand in year 2013 was 750. The forecast demand in year 2013 was 960. Using this data and a smoothing constant alpha of 0.3, which of the following is the resulting year 2014 forecast value? A. 766 B. 813 C. 897 D. 1,023 E. 1,120

C. 897 Forecast = 960 + 0.3 x (960-750) = 897

Which of the following is the portion of observations you would expect to see lying within a plus or minus 3 MAD range? A. 57.05 percent B. 88.95 percent C. 98.36 percent D. 99.85 percent E. 100 percent

C. 98.36 percent

Which of the following forecasting methodologies is considered a causal forecasting technique? A. Exponential smoothing B. Weighted moving average C. Linear regression D. Historical analogy E. Market research

C. Linear regression

In general, which forecasting time frame is best to detect general trends? A. Short-term forecasts B. Quick-time forecasts C. Long range forecasts D. Medium term forecasts E. Rapid change forecasts

C. Long range forecasts

Which of the following forecasting methods uses executive judgment as its primary component for forecasting? A. Historical analogy B. Time series analysis C. Panel consensus D. Market research E. Linear regression

C. Panel consensus

If a firm produced a product that was experiencing growth in demand, the smoothing constant alpha (reaction rate to differences) used in an exponential smoothing forecasting model would tend to be which of the following? A. Close to zero B. A very low percentage, less than 10% C. The more rapid the growth, the higher the percentage D. The more rapid the growth, the lower the percentage E. 50 % or more

C. The more rapid the growth, the higher the percentage

time series

Chronologically ordered data is referred to as a ________ ________

Linear, S-curve, asymptotic, exponential

Common trend types include:

1. Average demand for a period of time 2. Trend 3. Seasonal element 4. Cyclical elements 5. Random variation 6. Autocorrelation

Components of Demand:

CPFR Steps

Creation of a front-end partnership agreement, Joint business planning, development of demand forecasts, sharing forecasts, inventory replenishment

In business forecasting, what is usually considered a long-term time period? A. Three months or longer B. Six months or longer C. One year or longer D. Two years or longer E. Ten years or longer

D. Two years or longer

In time series data depicting demand which of the following is not considered a component of demand variation? A. Trend B. Seasonal C. Cyclical D. Variance E. Autocorrelation

D. Variance

Which of the following forecasting methodologies is considered a time series forecasting technique? A. Delphi method B. Exponential averaging C. Simple movement smoothing D. Weighted moving average E. Simulation

D. Weighted moving average

Decomposition Using Least Squares Regression

Decompose the time series into its components. *Find the seasonal component. *Deseasonalize the demand. *Find the trend component. Forecast the future values of each component. *Project the trend component into the future. *Multiply the trend component by the seasonal component.

Which of the following is not one of the basic types of forecasting? A. Qualitative B. Time series analysis C. Causal relationships D. Simulation E. Force field analysis

E. Force field analysis

Which of the following are used to describe the degree of error? A. Weighted moving average B. Regression C. Moving average D. Forecast as a percent of actual E. Mean absolute deviation

E. Mean absolute deviation

Random

Errors that are not explained by the model being used

Exponential smoothing techniques have become well accepted for six major reasons

Exponential models are surprisingly accurate. Formulating an exponential model is relatively easy. The user can understand how the model works. Little computation is required to use the model. Computer storage requirements are small because of the limited use of historical data. Tests for accuracy as to how well the model is performing are easy to compute.

error

Forecast ________ is the difference between the forecast value and what actually occurred

average

Forecast is the _____________ of a fixed number of past periods

Long Term Time series analysis

Forecasting greater than two years. useful for detecting general trends and identifying major turning points.

Causal relationship forecasting

Forecasting using independent variable other than time to predict future demand.

Causal relationship forecasting

Forecasting using independent variables other than time to predict future demand

1. Qualitative 2. Time series analysis 3. Causal relationships 4. Simulation

Four basic types of forecasts are common:

FITt equals

Ft + Tt

The formula for a simple moving average

Ft: Forecast for the coming period n: The number of average to be calculated At-1: Actual occurrence in the past period

The equations to compute the forecast including trend (FIT) are

Ft=FITt-1+α(At-1−FITt-1)[3.4]Tt=Tt-1+δ(Ft−FITt-1)[3.5]FITt=Ft+Tt[3.6] Ft=The exponentially smoothed forecast that does not include trend for period tTt=The exponentially smoothed trend for period tFITt=The forecast including trend for period tFITt−1=The forecast including trend made for the prior periodAt−1=The actual demand for the prior periodα=Smoothing constant (alpha)δ=Smoothing constant (delta)

The equation for a single exponential smoothing forecast is simply

Ft=Ft−1+α(At−1−Ft−1)[3.3] Ft: The exponentially smoothed forecast for Period t Ft −1: The exponentially smoothed forecast for the prior of Period t At−1: The actual demand in the prior period α: the desire respond rate or smoothing constant

The formula for a weighted moving average

Ft=w1At−1+w2At−2+···+wnAt−n[3.2] W1, W2, W3, wn: Weight to be given to the actual occurrence for the period t-n n: total number of periods in the forecast

Qualitative Forecasting techniques

Generally used to take advantage of expert knowledge Useful when judgment is required, when products are new, or if the firm has little experience in a new market. Examples: Market research Panel consensus Historical analogy Delphi method

zero; less

Ideally, MAD will be ________ (no forecasting error) Larger values of MAD indicate a _____ accurate model

decomposition

Identifying these elements and separating the time series data into these components is known as ______________________

Cyclical

Indicate other than annual recurrent periods of repetitive activity

straight

Linear regression is a special case which assumes the relationship between the variables can be explained with a ________________ line

Common trend types

Linear, S-curve, asymptotic, exponential

smoothing

Longer periods provide more ___________________

MAD equation form

MAD=∑t=1n|At−Ft|n[3.11] t=Period numberAt=Actual demand for the period tFt=Forecast demand for the period tn=Total number of periods||=A symbol used to indicate the absolute value disregarding positive and negative signs

Demand

MAPE scales the forecast error to the magnitude of ____________

Samples of qualitative forecasting techniques.

Market research, panel consensus, Historical analogy, Delphi method.

Strategic forecast

Medium and long-term forecast that are used to make decisions related to design and plans for meeting demand

Strategic forecasts

Medium- and long-term forecasts used to make decisions related to strategy and estimating aggregate demand

Multiple regression techniques

Often, more than one independent variable may be a valid predictor of future demand. Supported by statistical software

Smoothing constant alpha

Parameter in the exponential smoothing equation that controls the speed of reaction to differences between forecast and actual demand

Not component of demand

Planned

Four basis types of forecasting

Qualititive, time series analysis, casual relationships and simulation

Additive; multiplicative

Seasonal variation may be either _______________ or ___________________ (shown here with a changing trend)

Tatical forecast

Short-term forcasts used as input for making day to day decision related to meeting demand

Tactical forecasts

Short-term forecasts used as input for making day-to-day decisions related to meeting demamd

quickly

Shorter periods react to trends more ___________

Bias Random

Sources of error:

Qualiltive techniques

Subjective and judgemental, based on estimates and opinion

Mean absolute deviation (MAD)

The average forecast error using absolute values of the error of each past forecast

Forecasting

The basis of corporate planning and control

Forecast error

The difference between actual demand and what was forecast

Mean absolute percent error (MAPE)

The mean absolute deviation divided by the average demand; the average error expressed as a percentage of demand

Smoothing constant alpha (a)

The parameter in the exponential smoothing equation that controls the speed of reaction to differences between forecasts and actual demand

lag; delta

The presence of a trend in the data causes the exponential smoothing forecast to always ________ behind the actual data.This can be corrected by adding a trend adjustment The trend smoothing constant is _________ (𝛿)

Decomposition

The process of identify and separating time series data into fundamental components such as trend, seasonality

Decomposition

The process of identifying and separating time series data into fundamental components such as trend and seasonality

factor

The seasonal ___________ (or index) is the ratio of the amount sold during each season divided by the average for all seasons

A company has calculated its running sum of forecast errors to be 500 and its mean absolute deviation is exactly 35. Which of the following is the company's tracking signal? A. Cannot be calculated based on this information B. About 14.3 C. More than 35 D. Exactly 35 E. About 0.07

The tracking signal is RSFE/MAD = 500/35 = 14.29.

The characteristics help firm to choose the forecasting model

Time horizon to forecast Data availability Accuracy required Size of forecasting budget Availability of qualified personnel

Which forecasting is the linear regression used for

Time series forecasting and casual relationship forecasting

signal

Tracking ________ indicates whether forecast errors are accumulating over time (either positive or negative errors)

Bias

When a consistent mistake is made

Time series

____________ __________ analysis is based on the idea that data relating to past demand can be used to predict future demand

Casual

_____________ relationship forecasting uses independent variables other than time to predict future demand This independent variable must be a leading indicator

Regression

___________________ is used to identify the functional relationship between two or more correlated variables, usually from observed data

Decoupling

____________________ points occur when inventory is positioned in the supply chain to allow one operation to act independently of another

Bias errors

a consistent mistake is made

MAPE (Mean absolute percent error)

calculated by taking the MAD and dividing by the average demand = MAD/Average demand

Random errors

can be defined as those that cannot be explained by the forecast model being used.

MAD (mean absolute deviation)

computed using the differences between the actual demand and the forecast demand without regard to sign. It equals the sum of the absolute deviations divided by the number of data points

Short Term Time series analysis

forecasting less than three months. Used mainly for tactical decisions (e.g., replenishing inventory)

Medium term Time analysis

forecasting three months to two years. Used to develop a strategy which will be implemented over the next six to eighteen months (e.g., Meeting demand)

The major restriction in linear regression forecasting

it assume the project will fall in the straight line

Time frame using in forecasting

long, medium, short

Linear regression

refers to the special class of regression where the relationship between variables forms a straight line

seasonal factor

the amount of correction needed in a time series to adjust for the season of the year.


Conjuntos de estudio relacionados

Microm 301 Final Exam HW questions

View Set

OB: Chapter 1: Perspectives on Maternal, Newborn, and Women's Health Care

View Set