Statistics

Please answer the following time-series/forecasting questions:

1.
A medical device dealer in the local area wants to make an accurate forecast of demand for Super Sonic II Wheelchairs during the next month. Because the manufacturer is in Japan, it is difficult to send wheelchairs back or reorder if the proper number is not ordered a month in advance. From past sales records, the dealer has accumulated the following data on the Super Sonic II Wheelchairs over the past year:
Month Wheelchair Sales
January 9
February 7
March 10
April 8
May 7
June 12
July 10
August 11
September 12
October 10
November 14
December 16
Compute a 3-month moving average forecast of demand for April through January (of the next year).
Compute a 5-month moving average forecast of demand for June through January.
Compare the two forecasts of the 3-month and 5-month using MAD. Which forecast method should the dealer use?

2.
The Big City Hospital has experienced the following occupancy rates during the past 9 months:

Month Occupancy Rate (%)
1 83
2 78
3 75
4 81
5 86
6 85
7 89
8 90
9 86
Compute the exponential smoothing forecast with alpha=.2
Compute the exponential smoothing forecast with alpha=.2 and beta=.3 (you can use the results of first part and just add beta calculation)
Computer linear trend line forecast
Compare three forecasts using MAD and indicate which appears more accurate