Forecasting Part 2
Help!
|
|
||||
|---|---|---|---|---|---|
| F(sub)t (see slide 13 - variables) | forecast this period
🗑
|
||||
| F(sub)t-1 | forecast last period
🗑
|
||||
| A(sub)t-1 | actual demand
🗑
|
||||
| a (symbol for alpha?) | smoothing constant
🗑
|
||||
| time series methods assumptions | 1.this period's forecast is last period's forecast plus some error correction 2.all past actual demands are given exponentially decreasing weights 3. choice of value of "a" determines how much error correction 4.NOTES-makes sense when demand is steady
🗑
|
||||
| explanatory methods (see slide 14 and 15 for graph examples) | 1. simple regression 2. multiple regression 3. econometric models NOTES:1.idea of diminishing returns limits this model 2. you do not want to extrapolate beyond the range of known data because it could be way off
🗑
|
||||
| econometric models | all try to predict on (dependent) variable based on levels of other (independent) variables that are believed to have influence on the variable to be predicted
🗑
|
||||
| simple regression formula and sample graph (see slide 15) | Y (with a house top) = a + bX
🗑
|
||||
| line of best fit | defined by method of least squares
🗑
|
||||
| correlation (see slide 17 for correlation number line) | 1.answers how strong is the linear relationship between the variables 2. sample correlation coefficient ranges from -1 to +1 and measures degree of association 3. mainly used for understanding
🗑
|
||||
| " " **NOTES** | " " means negative correlation
🗑
|
||||
| correlation closer to 1 **NOTES** | the closer to 1 the better
🗑
|
||||
| correlation does not mean causation **NOTES** | (remember that)
🗑
|
||||
| perfect negative correlation | -1.0
🗑
|
||||
| no correlation | 0
🗑
|
||||
| perfect positive correlation | +1.0
🗑
|
||||
| increasing degree of negative correlation | 0 to -1.0
🗑
|
||||
| increasing degree of positive correlation | 0 to +1.0
🗑
|
||||
| guidelines for selecting a forecasting method (see slide 18 and 19) | 1. no pattern or direction in forecast error (slide 18) 2.smallest average forecast error - use either MAD (mean absolute deviation) or MSE (mean square error (MSE) see slide 19 for formulas
🗑
|
||||
| MAD - mean absolute deviation formula | **NOTES** absolute value is used because we don't want the terms to cancel each other out
🗑
|
||||
| forecasting method hints since it not an exact science | 1.longer time horizon, more dangerous to rely on past patterns 2.stable situation, use quantitative technique 3.longer time horizons use judgmental techniques 4. match method to data - trend, seasonal or cyclical 5.simpler methods more likely to be used
🗑
|
||||
| See slide 21 and 22 with NOTES for exponential smoothing example |
🗑
|
Review the information in the table. When you are ready to quiz yourself you can hide individual columns or the entire table. Then you can click on the empty cells to reveal the answer. Try to recall what will be displayed before clicking the empty cell.
To hide a column, click on the column name.
To hide the entire table, click on the "Hide All" button.
You may also shuffle the rows of the table by clicking on the "Shuffle" button.
Or sort by any of the columns using the down arrow next to any column heading.
If you know all the data on any row, you can temporarily remove it by tapping the trash can to the right of the row.
To hide a column, click on the column name.
To hide the entire table, click on the "Hide All" button.
You may also shuffle the rows of the table by clicking on the "Shuffle" button.
Or sort by any of the columns using the down arrow next to any column heading.
If you know all the data on any row, you can temporarily remove it by tapping the trash can to the right of the row.
Embed Code - If you would like this activity on your web page, copy the script below and paste it into your web page.
Normal Size Small Size show me how
Normal Size Small Size show me how
Created by:
rainesv