In: Statistics and Probability
National Scan, Inc., sells radio frequency inventory tags. Monthly sales for a seven-month period were as follows: Month Sales (000)Units Feb. 18 Mar. 17 Apr. 15 May. 22 Jun. 15 Jul. 24 Aug. 28 b. Forecast September sales volume using each of the following: (2) A five-month moving average. (Round your answer to 2 decimal places.) Moving average thousands (3) Exponential smoothing with a smoothing constant equal to .20, assuming a March forecast of 18(000). (Round your intermediate calculations and final answer to 2 decimal places.) Forecast thousands (4) The naive approach. Naive approach thousands (5) A weighted average using .60 for August, .20 for July, and .20 for June. (Round your answer to 2 decimal places.) Weighted average thousands
(1) Moving Average : For 'n' months moving average we need to first calculate the total of first 'n' months. We then divide that by 'n'. This gives the forecast for 'n+1'th month. Then again with every next month we will do the same calculations. With every next set,the first month would get eliminated and next month would join.
Eg: Forecast for Aug=
Month | Sales(000) | Moving total | Moving average (000) |
Feb | 18 | ||
Mar | 17 | ||
Apr | 15 | ||
May | 22 | ||
Jun | 15 | ||
Jul | 24 | 87 | 17.40 |
Aug | 28 | 93 | 18.60 |
Sep | 104 | 20.80 |
Forecast for Sep is 20800.
(2) Exponential smoothing has the following formula
where are actual and forecast values at time 't' and is the smoothing constant
= 0.20 and Forecast for Mar = 18
Eg Forecast for Apr = Actual of Mar * 0.2 + (1 - 0.2) * Forecast of Mar
Month | Sales(000) | Forecast |
Feb | 18 | |
Mar | 17 | 18.00 |
Apr | 15 | 17.80 |
May | 22 | 17.24 |
Jun | 15 | 18.19 |
Jul | 24 | 17.55 |
Aug | 28 | 18.84 |
Sep | 20.67 |
Forecast for Sep is 20670.
(3) Naive approach simply means that history my repeat itself. That is the trends or the seasonal changes might be same for the next periods too. Some example of these approach are moving avg, weighted avg. The one that is not separately asked.
Since data before Feb is not given we will begin by forecasting for March.
Month | Sales(000) | Forecast |
Feb | 18 | |
Mar | 17 | 18 |
Apr | 15 | 17 |
May | 22 | 15 |
Jun | 15 | 22 |
Jul | 24 | 15 |
Aug | 28 | 24 |
Sep | 28 |
Forecast for Sep is 28000.
(4) The weighted avg uses weights for previous values. These weights are multiplied by their actual values and their sum is taken. The sum is divided by the total of the weights. This is the forecast value.
Month | Sales | Weights |
Jun | 15 | 0.2 |
Jul | 24 | 0.2 |
Aug | 28 | 0.6 |
Forecast for Sep =
= 24.6 * 1000
Forecast for Sep is 24600.