Read the Gasoline Demand Case and use the data provided in the file Gasoline Demand Data to answer the following questions. Your answers should provide clear and unambiguous recommendations. Please provide explanations for your answers and any outputs that you feel are needed to support your argument.
- Calculate a 95% confidence interval for the average gasoline consumption of a household.
- Calculate a 95% confidence interval for the average gasoline consumption of a household:
(a) In an urban area.
(b) Consisting of a young and single person.
- Do you agree with the client executives’ claim regarding the average household consumption for the two targeted segments (urban households and the young, single households)?
Why or why not?
- Assume both proposed advertising campaigns cost the same. If only one campaign is to be launched, which of the two campaigns would you recommend launching? Why?
- You will not learn anything more about campaign costs before the recommendation deadline, but still have to provide an unambiguous and unconditional recommendation. What would be your recommendation to the client regarding whether or not to launch both campaigns simultaneously?
Why?
Background
Gasoline Demand Case
Understanding product demand and customers’ needs often separate a healthy business model from a failed one. In particular, demand estimation often determines success in several industries (airline, energy, etc.) and business disciplines (marketing, supply chain, etc.). Such estimation can be challenging since it requires both access to the relevant data and a workable knowledge of the appropriate statistical techniques. Some consulting firms have created an opportunity out of this challenge by acquiring “brains” capable of creating valuable quantitative models, while guiding the clients to collect and provide relevant data.
Co-Innovation, a major consulting company, has been famous for its successful application of quantitative methods to provide valuable insights to a variety of industries. Pierre Ledoux has recently joined the Data Analysis and Statistics division at Co-Innovation after obtaining his MBA. He has become part of a team of consultants sent to Toronto to provide an expert opinion on the Canadian gasoline market to a client company operating gas stations across Canada.
Client meeting
Pierre and the team just finished a long meeting with the client. Executives from the client company have given a tight Monday deadline for the submission of a recommendation. The client hired Co-Innovation to provide advice on the choice of an upcoming advertising campaign. The client has two campaigns ready for launch, both heavily relying on radio ads and sponsorships of traffic updates on the most popular radio stations across Canada. The goal of the campaigns is to increase overall gasoline sales for the targeted market segment. One of the prepared campaigns targets households in urban areas, while another targets young and single consumers. Executives from the client company claim that their proprietary sales data indicate the average gas consumption for both target segments to be smaller than the consumption in their respective counterparts (rural households, not young or not single). Based on experience with several prior campaigns, the client executives are willing to assume that the advertising campaign would be able to bring the target segment’s average gas consumption to the same level as its counterpart.
Despite several requests by Shreya Talagrand, a senior consultant at Co-Innovation, the exact figures for the cost of the advertisement campaigns were not disclosed. However, the client executives mentioned a 20% discount on the cost of each of the advertising campaigns, if both of them are launched simultaneously.
During the meeting, Pierre quickly requested access to the client’s data on the gasoline market. The client was initially willing to provide only aggregate sales information. Pierre argued that such data might be insufficient and could severely compromise the team’s ability to make quantitative estimates of consumer demand. Shreya skillfully and rather quickly convinced the executives that releasing more detailed data at the level of individual customers is critical for the Co-Innovation team to be able to provide a valuable recommendation to the client. However, the proprietary data the client had available consisted only of gasoline purchases made by credit cards without any demographic information about the associated household.
After additional discussions, the executives agreed that the data provided by the National Private Vehicle Use Survey are very representative of the whole population and all of its seg- ments. The data are maintained by the Canadian government and provide detailed demographic information on randomly selected households. It also tracks the gasoline consumption habits of each household over a month-long period. The data contain information of 5,001 randomly selected households col- lected in the file GasolineDemandData.xlsx. Pierre was partic- ularly motivated to work with such detailed information, which seemed enough for Shreya to move the discussion to other is- sues.
Living up to the standard
After the meeting, Shreya approached Pierre and asked him if he was familiar with Co-Innovation’s policies. She went on to explain that decisions need to be well thought out and sup- ported by data. In Shreya’s view, each recommendation is as important for the current client as it is for Co-Innovation’s ability to acquire future clients. Thus, no matter how small a
recommendation is, it always matters.
Sample Solution
The post Gasoline Demand Case appeared first on homework handlers.
