Case Study 4—Choosing a Sales Forecasting Model: A Trial and Error Process
Let's pick up where we left off at the end of Case Study 2 with the XYZ Motel. Having determined that there is no upward trend in the monthly data, we need to choose a forecasting model that produces a result that approximates last year's sales for the same four-month period. While a seasonally adjusted time series model probably does the job very nicely, in this case study we would like to demonstrate a cross-sectional or causal model. Since the period of interruption was closed, a search was made for an independent variable that would correlate closely with the motel's sales. The gross sales for lodging places for the Brunswick Economic Summary Area (ESA) was found and downloaded from the State Planning Office that coincided with the 36 months prior to the incident date and the four months of the period of interruption. Since the monthly sales of the XYZ Motel are included in the monthly ESA data, they were subtracted from the monthly ESA data so as not to distort comparability between the two sets of data.
An advantage of using data external to the plaintiff's records is that the sales forecast is based on independent, corroborating, third-party data, thereby heightening relevance and reliability.
Correlation with Industry Sales
Comparing the monthly percentage of total sales and the cumulative monthly percentage of sales for the motel versus the Brunswick ESA during the subject four months, ...