Harmon foods, inc.

Solo disponible en BuenasTareas
  • Páginas : 2 (357 palabras )
  • Descarga(s) : 0
  • Publicado : 6 de junio de 2011
Leer documento completo
Vista previa del texto
In order to built a model to forecast next year’s sales we will analyze past internal data plus the data provided by the National Association of Cereal Manufacturers regarding seasonality. We willlook at the following factors:
• Consumer packs
• Dealer allowances
• Sales seasonality
We will use external data for the seasonality because, as it will be explained later, other internal policies(consumer packs or dealer allowances) have a big impact on sales and therefore our past sales may follow a different seasonal pattern due to this policies (we would be double counting some factors).The objective of this analysis is finding a correlation between these factors and the monthly shipments so that, by determining these variables a forecast can be done.
For all the analysis, thefirst 12 months of data will not be taken into account as are incomplete (there are no shipments to relate the variables to)
Consumer packs
The correlation between Consumer packs and monthly shipmentsis described by the following function:
Shipments = 339746 + 0.42*consumer packs + e
This variable has a significant correlation (t-ratio 3.797) and explains 24% of the shipments (R2).
Dealerallowances
The correlation between dealer allowances and monthly shipments is described by the following function:
Shipments = 346887 + 0.071*dealer allowances + e
This variable has a significantcorrelation (t-ratio 4.374) and explains 29% of the shipments (R2).
As both this variables are set by the company and have a great impact on the monthly shipments, in order to analyze the impact ofseasonality we have to look at external data.
Seasonality
The correlation between seasonality (base on the industry index) and monthly shipments is described by the following function:
Shipments =197703 + 5797*seasonality index + e
This variable has a significant correlation (t-ratio 6.45) and explains 47% of the shipments (R2).
By combining all these variables into one model, we find...
tracking img