OPMA 3306

What time horizons are used for strategic forecasts?

Medium & long-term

A forecast based on average past demand is a

Moving average forecast

When the amount of seasonal variation depends upon the trend or average amount, the seasonality is described as

Multiplicative Seasonality

What are the sources or random error?

error that is not explained by the forecasting model

What are the sources of bias error?

the failure to include the right variables; the use of the wrong relationships among variables; employing of the wrong trend line; a mistaken shift in the seasonal demand from where it normally occurs; and the existence of some undetected secular trend

In the formula for exponential smoothing (At-1 - Ft-1) represents

the forecast error for last period

When you are trying to determine whether a forecast is keeping pace with changes in demand, you should use which measure?

tracking signal

Which time series forecasting model uses weights that decrease at a rate of (1- a) for each past period?

Exponential

A qualitative forecasting technique that is useful for identifying what consumers like and dislike about a product is

Market research

What is the process for forecasting the future values of each component

Project the trend component into the future, multiply the trend component by the seasonal component

Which is the larger measure, the standard deviation or MAD?

Standard deviation

What type of forecast is used for day-to-day decision making?

Tactical

all of the following are reasons why exponential has become well accepted except: formulating the model is easy, low computer storage requirements, tests for accuracy are difficult, models are surprising accurate

Tests for accuracy are difficult

True or false: the weights in a weighted moving average can be adjusted to account for seasonal data

True

What is the process for decomposing the time series into its components?

find the seasonal component, deseasonalize the demand, find the trend component

smoothing constants must be given a value between

0 and 1

The weight on each element in a weighted moving average must equal

1

Which of the following is true about the relationship between standard deviation and mean absolute deviation? MAD and standard deviation are equal, there is no relationship, 1 standard deviation is approximately 1.25 MAD, 1 MAD is approximately 0.8 standard deviation

1 standard deviation is approximately 1.25 MAD, 1 MAD is approximately 0.8 standard deviation

When the change in demand due to seasonally is a constant amount, regardless of trend or average, the seasonal variation is describes as

Additive Seasonal Variation

Which smoothing constant controls the speed of reaction to differences between forecasts and actual demand?

Alpha

Using the number of cars passing by a restaurant to predict sales is an example of which type of forecasting ?

Causal relationship forecasting

What term describes the process of identifying & separating time series data into components?

Decomposition

True or False: Qualitative forecasts typically involve mathematical calculations

False

Which measure of error calculates the average absolute value of the actual forecast error?

MAD

Which measurement of error represent the average error measured as a percentage of average demand?

MAPE

When considering more than one variable, along with the effects of each variable on the item of interest, which forecasting model should be used?

Multiple regression

Which forecasting model is based upon average past demand?

Simple moving average

What type of forecast should be used for strategy, sourcing & location decisions?

Strategic

The exponentially smoothed trend for period t (Tt) includes the error between

The previous forecast and the previous forecast including trend

True or False: Mean Absolute Deviation calculates the average absolute value of the forecast error

True

True or False: The seasonal factor is also known as the seasonal index

True

True or false: regression relationships are usually developed from observed data

True

Bias errors occur when

a forecast is consistently too high (or too low)

Mean Absolute Percent Error represents the average error as

a percentage of average demand

The main disadvantage of the moving average is that

all individual data elements must be carried as data

A simple moving average gives ________ weight to each component of the forecast; whereas a weighted moving average gives __________ weight to each element

equal; varying

Which of the following statements is true about linear regression forecasting? linear regression is used for time series forecasting, linear regression is used for causal forecasting, linear regression estimates demand using a line of the form Y = a+bt , linear regression has no serious drawbacks

linear regression is used for time series forecasting, linear regression is used for causal forecasting, linear regression estimates demand using a line of the form Y = a+bt

Which of the following are examples of qualitative forecasting? market research, panel consensus, linear regression analysis, time series analysis

market research, panel consensus

What are attributes of the panel consensus forecasting technique?

may be difficult to get full participation from all members, relies on larger group to develop accurate forecast

To adjust for trends, exponential smoothing uses a second smoothing constant called

delta

What are attributes of the marketing research forecasting technique?

often involves marketing surveys, useful for identifying attractive attributes of competitive products

What are attributes of the delphi method forecasting technique?

requires a moderator, may require several rounds to achieve results

The exponential forecasting model uses all the following data except: actual demand for most recent forecast period, smoothing constant alpha, most recent forecast, smoothing constant delta

smoothing constant delta

When including trend effects in exponential smoothing, how many smoothing constants are required?

two (alpha and delta)

One way to overcome the major restriction of linear regression forecasting is to

use a shorter time period

What are attributes of the historical analogy forecasting technique?

useful when a similar product already exists