use the Betty Spaghetty experiment, pdf pages 149-150 provided below) to

(a) test for difference in means between test vs controls for both products (watch the # of stores), (b) provide a unit sales forecast with and without ads (use the "sales potential" information and the "represented X% of sales" information), (c) estimate profits with and without ads for Arizona and California (assume they are running the same ad that was used in the experiment, ie treat the development of the ads as a sunk cost, and the 3M ad budget in this roll-out is the national total, i.e. you need to adjust it for Arizona and California combined based on population (tracks with the retailer's national sales percentages))

In other words, you only do AZ and CA; you need to think of them as one joint market; the 3M national ad budget needs to be prorated for AZCA based on population (the 12 and 2 figure can be used for this purpose (actual numbers are 12.18 and 2.12)

The purpose of this is to understand the benefits of employing experiments in an applied context as well as bringing the pricing margin issues into sharper focus.

One Ohio Art executive worried that the test would be difficult to read and suggested that a split-cable test could be implemented in April of the following year for about $500,000.9He believed the estimate of the projected sales lift from such a split-cable test would be much more accurate. The suggested retail price for EAS was \$12.99. The Travel, Pocket, and Mini Etch A Sketch were less expensive at $8.99,$4.99, and $2.99, respectively. Given unit sales for each product, the weighted average of all EAS products sold in the holiday time period was $10.00. It was this $10.00 price that was suggested for use in calculating the percentage increase required for a national campaign. The suggested retail price for Doodle Doug was $14.99. The company's average gross margin for the EAS products was 58%, and the average retail margin was 36%. (See Figure 2 for pictures of the EAS and Doodle Doug.) Figure 2. EAS and Doodle Doug toys. Source: Ohio Art. Used with permission. The Betty Spaghetty Experiment In mid-2007, the company implemented another field experiment for a revamped Betty Spaghetty product line. The test had three objectives: (1) estimating consumer demand for the revised Betty Spaghetty line, (2) testing whether advertising could increase sales (and profits) obtained for the redesigned Betty Spaghetty, and (3) convincing the merchandise manager at a mass-merchant chain that those sales of Betty Spaghetty would justify the allocation of shelf space. For the Betty Spaghetty experiment, television and radio commercials were aired in Arizona for four weeks from June 17, 2007, to July 14, 2007. The company purchased 600 gross rating points (GRPs) for the television advertisements for a total cost of $31,500. The ads were aimed at girls between the ages of 2 and 11 and were aired on local cable channels, such as Nickelodeon and the Cartoon Network. Management also purchased 64 GRPs for radio 9 Split-cable testing systems allow for delivery of separate advertising campaigns or a different level of advertising exposures to different groups of households within a given market and tracked purchases through consumer diaries or other panel data. This eliminated differences in retail environments, competitive activity, and other market characteristics among test and control groups. commercials for a total cost of $8,022. The radio commercials were aired during morning and evening commutes. Each of the television and radio programs selected for the commercials reached about 1.8% of the population in Phoenix. The cost of developing the commercial through an outside agency was $150,000. Management estimated that an equivalent ad budget for eight to ten weeks of preholiday advertising, factoring in certain economies as well as the higher seasonal cost of media, would be approximately $3 million. The average retail selling price of Betty Spaghetty during the test was about $15.00. Retailer and Ohio Art margins were about the same as for EAS, 36% and 58%, respectively. Given that some time would be required to read the test, obtain shelf space, and ship product to stores, management estimated that the four-week test market sales period represented about 10% of the total remaining sales potential for the year. Table 4 reports weekly sales in 23 Arizona stores (test) and in 24 stores of the same mass merchant in California (control) for two versions of Betty Spaghetty. The stores represented 50\% of the retailer's Arizona sales and 10% of California sales, respectively. Arizona and California represented 2% and 12%, respectively, of the retailer's national sales, and that same retailer was expected to account for 25% of total Betty Spaghetty sales. Management intended to use the test to help estimate Betty Spaghetty sales with and without advertising. Table 4. Weekly unit sales of Betty Spaghetty in test and control cities