| Term | Definition |
|---|
| Forecast | A statement about the future value of a variable of interest (demand); These affect decisions and activities throughout an organization. |
| Determine the purpose of forecast | Step 1 in the Forecasting Process |
| Time Series | Uses historical data assuming the future will be like the past (data/time) |
| Associative Models | Uses explanatory variables to predict the future (look at the relationships); time is not a factor |
| Seasonality | Short-term regular variations in data |
| Cycle | Wave-like variations of more than one year's duration |
| Irregular Variations | Caused by unusual circumstances |
| Random Variations | Caused by chance |
| Naive Forecast | The forecast for any period equals the previous period's actual value; forecast lags behind actual by 1 period; simple to use |
| Moving Average | Averages a number of recent actual values, updated as new values become available (a simple average). |
| Weighted Moving Average | Recent values in a series are given weights in computing a forecast |
| Exponential Smoothing | Weighted averaging method based on previous forecast plus a % of the forecast error (Actual-Forecast) |
| Beta | Coefficiant called the smoothing constant. It is the % feedback. |
| Forecast Error | The difference between the actual value and the predicted value |
| MAD | The average of the absolute deviations. = Sum (Actual - Forecast)/n |
| a = intercept; bt = slope. | Which is the slope and which is the intercept? a + bt |
| MSE | The average of the squared errors. = Sum (Actual - Forecast)2 / n-1 |
| Linear Trend Forecasts | Which trend forecast will we use most? |
| Slope | Unit change in the forecast for each period of time |
| Intercept | Value of the forecast at t=0 |
| Correlation Coefficient | r is = to what? It expresses the degree of strength of the linear relationship between the independant and dependant variables |
| Coefficient of Determination | r2 is = to? It expresses the percent of variation in the dependant variable Y that is explained by the regression equation. |
| Establish a time horizon | Step 2 in Forecasting process |
| Select a forecasting technique | Step 3 in Forecasting process |
| Gather and analye data | Step 4 in Forecasting process |
| Prepare the forecast | Step 5 in Forecasting process |
| Monitor the forecast | Step 6 in Forecasting process |
| Decision Theory | A general approach to decision making which is suitable for a wide range of operations management decisions; universal |
| Alternatives | Manager chooses these; various choices |
| Payoffs | There is one of these for each alternative under each possible future condition; conditional value; dependant; monetary value |
| Conditional Values | Also known as payoffs |
| States of Nature | Outcomes; things of which you have little or no control |
| Certainty, Risk, Uncertainty | Three decision making environments |
| Certainty | The outcome of every alternative. You will always choose the best choice. |
| Risk | An environment in which certain future events have probabilities associated with each outcome |
| Uncertainty | Environment in which it is impossible to assess the probabilities for each outcome (only estimate) |
| Maximax | Optimistic approach; Alternative with the best payoff |
| Maximin | Alternative with the best of the worst possible payoffs; pessimistic approach |
| Minimax Regret | Alternative that has the least of the worst regrets (not making the right choice) |
| Laplace | Alternative with the best average payoff of any alternatives |
| EMV (Expected Monetary Value) | Weighted average; Expected profit of each alternative |
| EVPI | Difference between the expected payoff with perfect information and the expected payoff under risk EPC - Max EMV |
| Decision Tree | A schematic or graphical representation of the alternatives and their possible consequences (outcomes) |
| Suboptimization | Different departments each attempt to reach a solution that is only optimal for that department |
Combine with other sets
Share on Facebook
Share on MySpace
!