Applying Time Series Methodologies MemoMEMORANDUMTO: Myra Reid VP ProductionFROM: Jonathan ChretienDATE: June 10, 2010SUBJECT:Forecast and ExplanationBased on the time series methodologies and analysis of the past data, my forecast for the unit production in next four quarters should be 12.00, 14.00, 13.00 and 20.00 million respectively. This is arrived at taking into consideration the past quarterly data of six years and using centred moving averaging model. I have done three phase research to arrive at these values.In the first phase, it was researched and decided what variable explains the advertising budget. There were three variables to choose from previous year sales, competitor’s advertising budget and retail coverage. This decision was taken based on the correlation co-efficient 0.96 and based on the regression analysis. The regression analysis shows that standard error of the prediction with sales as the independent variable is 11.00. This is lower than the standard error of the estimate for the other two variables.
This is the end of the preview.
access the rest of the document.