Upcoming SlideShare
×

# IBM401 Lecture 10

729 views

Published on

0 Likes
Statistics
Notes
• Full Name
Comment goes here.

Are you sure you want to Yes No
• Be the first to comment

• Be the first to like this

Views
Total views
729
On SlideShare
0
From Embeds
0
Number of Embeds
2
Actions
Shares
0
34
0
Likes
0
Embeds 0
No embeds

No notes for slide

### IBM401 Lecture 10

1. 1. Quantitative Analysis for Business<br />Lecture 10<br />September 13th, 2010<br />http://www.slideshare.net/saark/ibm401-lecture-10<br />
2. 2. Example i<br />Data shown is average monthly production of a commodity for the year 1948 – 1958<br />Construct a 5 year moving average<br />Construct a 4 year centered moving average<br />
3. 3. Example ii<br />Monthly sales of A4 copy paper have been recorded over 12 months (Year 1)<br />Using F0 = 1700, which α do you recommend?<br />α = 0.2<br />α = 0.5<br />From selected α, calculate Trend using β = 0.1 and T0 = 100<br />
4. 4. Example ii<br />Supposed sales team has come back with additional data of Year 2 sales, find seasonal index using 4 period centered-moving-average<br />Deseasonalize the data<br />
5. 5. Example ii<br />Using the Forecast method obtained from part 1 of this question, calculate tracking signal of June of year 1. <br />
6. 6. solution<br />
7. 7. Example i<br />5-year moving average <br />MA5-year = (Ft-5 + Ft-4 + Ft-3 + Ft-2 + Ft-1)/5<br />4-year centered MA<br />CMA4-year = (0.5*(Ft-2 + Ft+2) + (Ft + Ft-1 + Ft-2))/4<br />
8. 8. Example i<br />5-year moving average & 4-year centered MA<br />
9. 9. Example ii<br />Determining which α, choose the one with lowest MAD<br />New forecast = Last period’s forecast<br /> + (Last period’s actual demand - Last period’s forecast)<br />
10. 10. Example ii<br />
11. 11. Example ii<br />
12. 12. Example ii<br />calculate Trend using β = 0.1 and T0 = 100<br />
13. 13. Example ii<br />
14. 14. Example ii<br />Find seasonal index using 4 period centered-moving-average<br />Use CMA formula<br />Deseasonalizethe data<br />Find seasonal index from CMA<br />st = Actualt / CMAt<br />
15. 15. Example ii – Find CMA and seasonal index<br />
16. 16. Example ii – Find average seasonal index<br />
17. 17. Example ii - deseasonalize<br />
18. 18. Example ii<br />Using the Forecast method obtained from part 1 of this question, calculate tracking signal of June of year 1<br />RSFE = Ratio of running sum of forecast errors <br /> = ∑(actual demand in period i - forecast demand in period i)<br />
19. 19. Example ii – Tracking signal<br />
20. 20. Example ii<br />June, Year 1 Tracking signal<br />