Chapter 3: Forecasting Flashcards
A statement about the future value of a variable of interest.
Forecast
The first basic step in the forecasting process
Determine the Purpose of the Forecast
The second basic step in the forecasting process.
Establish a Time Horizon
The third basic step in the forecasting process.
Obtain, clean, and analyze appropriate data
The fourth basic step in the forecasting process
Select a forecasting technique
The fifth basic step in the forecasting process
Make the forecast
The sixth basic step in the forecasting process
Monitor the forecast errors
Difference between the actual value and the value that was predicted for a given period.
Error
The average absolute forecast error.
Mean Absolute Deviation
The average of squared forecast errors.
Mean Squared Error
The average absolute percentage error.
Mean Absolute Percent Error
Approach to forecasting that consists mainly of subjective inputs.
Qualitative
Approach to forecasting that involves either the projection of historical data or the development of associative models that attempt to use causal variables to make a forecast.
Quantitative
Type of information which includes human factors, personal opinions, and hunches.
Soft Information
Type of data that is objective information.
Hard Data
Forecasts that use subjective inputs such as opinions to form consumer surveys, sales staff, managers, executives, and experts.
Judgmental Forecasts
Forecasts that project patterns identified in recent time-series observations.
Time-Series Forecasts
Forecasting technique that uses explanatory variables to predict future demand.
Associative Model
An iterative process in which managers and staff complete a series of questionnaires, each developed from the previous one, to achieve a consensus forecast.
Delphi Method
A time-ordered sequence of observations taken at regular intervals.
Time Series
A long-term upward or downward movement in data.
Trend
Short-term regular variations related to the calendar or time of day.
Seasonality
Wavelike variations lasting more than one year.
Cycle
Caused by unusual circumstances, not reflective of typical behavior.
Random Variations
A forecast for any period that equals the previous period’s actual value.
Naive Forecast
Technique that averages a number of recent actual values, updated as new values become available.
Moving Average
More recent values in a series are given more weight in computing a forecast.
Weighted Average
A weighted averaging method based on previous forecast plus a percentage of the forecast error.
Exponential Smoothing
Using the forecasting method that demonstrates the best recent success.
Focus Forecasting
Used to develop forecasts when trend is present.
Linear Trend Equation
Linear Trend Equation
Ft = a + bt
Variation of exponential smoothing used when a time series exhibits a linear trend.
Trend-Adjusted Exponential Smoothing
Regularly repeating movements in series values that can be tied to recurring events.
Seasonal Variations
The seasonal percentage applied in the multiplicative model.
Seasonal Relative
Variables that can be used to predict values of the variable of interest.
Predictor Variables
Technique for fitting a line to a set of points.
Regression
Minimizes the sum of the squared vertical deviations around the line.
Least Squares Line
A measure of the scatter of points around a regression line.
Standard Error of Estimate
A measure of the strength and direction of relationship between two variables.
Correlation
A visual tool for monitoring forecast errors.
Control Chart
The ratio of cumulative forecast error to the corresponding value of MAD, used to monitor a forecast.
Tracking Signal
Persistent tendency for forecasts to be greater or less than the actual values of a time series.
Bias
Type of error that occurs when the forecast is too low.
Positive Error
Type of error that is the difference between the actual and predicted values in a given period.
Forecast Error
Type of error that occurs when the forecast is too high.
Negative Error
Alternate name for seasonal relative.
Seasonal Index
The essence of associative techniques is the development of an equation that summarizes the effects of _____
Predictor Variables
In time-series data, _____ are regularly repeating upward or downward movements in series values that can be tied to recurring events.
Seasonal Variations
_____ forecasts pertain to ongoing operations.
Short-term
_____ forecasts are an important strategic planning tool.
Long-term
Represents an error of zero on a control chart.
The Center Line
Linear Trend Equation
F=a+bt
Exponential Smoothing Forecast
Ft = Ft-1 + a(At-1 - Ft-1)
Formula for error in period t
et = At-Ft
A value of 0.25 or less of r^2 indicates a _____ predictor.
Poor
A value between 0.25 and 0.8 of r^2 indicates a _____ predictor.
Moderate
Formula for trend-adjusted exponential smoothing forecast.
TAFt+1 = St + Tt
Represents the absolute forecast error.
MAD
Measures the percentage of variation in the values of the dependent variable that is “explained” by the independent variable.
R^2
Model in which predictions are made on demand for an established product.
Diffusion Model
Often used to develop long-range plans and new product development.
Executive Opinions
A tracking signal compares the cumulative forecast error to the MAD in order to detect any _____ over time.
Bias
In the equations for the coefficients of a line, what is the a term?
Intercept
In the equations for the coefficient of a line, what is the b term?
Slope
In the equations for the coefficients of a line, what is the y term?
Value of the time series
