Bass Forecasting Tutorial - Run Analysis

Each model includes a sample data set (OfficeStar) that can be found under the Tutorials dropdown on the Enginius Dashboard.

The remainder of the tutorials use the Bass OfficeStar data set as the starting data set.

OfficeStar Data Blocks

Bass Forecasting Run Analysis Setting (OfficeStar Default Settings)

Bass forecasting requires:

Forecasts

• Number of periods: The number of periods for the forecast. If you have past data, those periods should be included in this number (e.g. enter 25 for number of periods if you have 10 periods of past data and 15 periods to forecast).
• Type of market potential:  Select whether your market potential is fixed or variable. If variable, select the data block that contains your variable market potential data.

Parameter estimates

• Manually-set parameters: Enter your own p and q values. Roughly speaking, p is the proportion of non-adopters who would adopt the product in the current period, independent of whether others adopt the product.  Typically, its value is in the range 0.01 to 0.05, with an average around 0.035.  q ranges from low values of around 0.01 to 1.0, with an average equal to 0.4.  If q is equal to 1, it means that when a non-adopter hears about the product from an adopter, it is nearly certain that the non-adopter would adopt the product.  If q is equal to 0.1, it means (roughly speaking) that a non-adopter would have to be exposed to 10 adopters before being convinced to adopt the product.  
• Estimated parameters from data: Select the data block that contains your cumulated adoptions observed in the past. p andq values will be calculated from the past data during analysis and used for forecasting.
• By analogy: Select similar products for which the parameters have already been estimated. If you wish to run the analysis with different parameters estimated from various products, repeat these steps for each scenario in your model to populate the p and q values for forecasting.  The first dropdown (optional) in the row allows filtering by categories while the second dropdown will contain the analogous product.

Generalized Bass model (options only available if you check “Advanced” at bottom)

• Advertising Coefficient (Generalized Bass model only): The percentage increase in speed of market penetration with a 1% increase in advertising. The advertising coefficient does not change the number of potential adopters, but rather, it changes the speed at which they adopt; it reflects the percentage increase in the speed of market acceptance with a 1% increase in advertising. (Recall that the documented values for the advertising coefficient typically range between 0.3 and 1.).  For completely new technologies for which advertising drives product awareness and knowledge, the coefficient will be closer to the higher end of the range.  For products such as TV and mobile phones, where there is at least some knowledge of the product category (e.g., familiarity with the general product category, and how the product is used), the advertising coefficient is likely to be closer to the lower end of the range.  
• Price Coefficient (Generalized Bass model only): The percentage increase in speed of market penetration with a 1% decrease in price. The price coefficient reflects the percentage increase in speed of market acceptance with a 1% decrease in price. The Price coefficient has a wide range of feasible values from 0% to 4%.  For some categories, price may be very critical (e.g., discretionary items), and the coefficient value could be high.  For other categories (e.g., necessities), the price coefficient is likely to be small.  In some rare cases (e.g., high-end products), the price coefficient could even be negative.
• Relative price and advertising: Select the data block that contains your relative price and advertising data.
• Market Price Elasticity (Generalized Bass model only): The percentage increase of market potential with a 1% decrease in price. There is no precise way to determine a good answer for this question, but the following guidelines should be useful.  Typically, in the initial stages of a product's introduction, prices are high, but the demand is inelastic (i.e., elasticity is near 0) because innovators are not price-driven. If price falls below, say $500 for a household durable, then it enters into the price-elastic mass market. Estimates of price elasticity in this situation are typically in the range of 0.1 to 0.5 (i.e., a 0.1% to 0.5% increase in market potential for a 1% decrease in price).

Your Enginius report can be generated in many different formats. Clicking the globe beside the Run button will allow you to select a new report format.

After selecting the desired model options, click  to generate the report in the desired format.