Glossary
- Adaptive Smoothing
The process of automatically monitoring and adjusting the smoothing constants in an exponential smoothing model.
- Bias
A technique for determining the accuracy of a forecasting model by measuring the average error and its direction.
- Causal Models
Models that forecast using variables and factors in addition to time.
- Centered Moving Average
An average of the values centered at a particular point in time. This is used to compute seasonal indices when trend is present.
- Cyclical Component
A pattern in which the annual data in a time series tend to repeat every several years.
- Decision-Making Group
A group of experts in a Delphi technique that has the responsibility of making the forecast.
- Decomposition
A forecasting model that decomposes a time series into its seasonal and trend components.
- Delphi
A judgmental forecasting technique that uses decision makers, staff personnel, and respondents to determine a forecast.
- Deseasonalized Data
Time-series data in which each value has been divided by its seasonal index to remove the effect of the seasonal component.
- Deviation
A term used in forecasting for error.
- Error
The difference between the actual value and the forecast value.
- Exponential Smoothing
A forecasting method that is a combination of the last forecast and the last observed value.
- Least Squares
A procedure used in trend projection and regression analysis to minimize the squared distances between the estimated straight line and the observed values.
- Mean Absolute Deviation (MAD)
A technique for determining the accuracy of a forecasting model by taking the average of the absolute deviations.
- Mean Absolute Percent Error (MAPE)
A technique for determining the accuracy of a forecasting model by taking the average of the absolute errors as a percentage of the observed values.
- Mean Squared Error (MSE)
A technique for determining the accuracy of a forecasting model by taking the average of the squared error terms for a forecasting model.
- Moving Average
A forecasting technique that averages past values in computing the forecast.
- Naïve Model
A time-series forecasting model in which the forecast for next period is the actual value for the current period.
- Qualitative Models
Models that forecast using judgments, experience, and qualitative and subjective data.
- Random Component
The irregular, unpredictable variations in a time series.
- Running Sum of the Forecast Errors (RSFE)
Used to develop a tracking signal for time-series forecasting models, this is a running total of the errors and may be positive or negative.
- Seasonal Component
A pattern of fluctuations in a time series above or below an average value that repeats at regular intervals.
- Seasonal Index
An index number that indicates how a particular season compares with an average time period (with an index of 1 indicating an average season).
- Smoothing Constant
A value between 0 and 1 that is used in an exponential smoothing forecast.
- Time-series Model
A forecasting technique that predicts the future values of a variable by using only historical data on that one variable.
- Tracking Signal
A measure of how well the forecast is predicting actual values.
- Trend Component
The general upward or downward movement of the data in a time series over a relatively long period of time.
- Trend Projection
The use of a trend line to forecast a time series with trend present. A linear trend line is a regression line with time as the independent variable.
- Weighted Moving Average
A moving average forecasting method that places different weights on past values.