Nov. 7, 2006 ECON 240A-1 L. PhillipsTake-home I : Tuesday Nov. 21I. Your report should have an executive summary of one to two pages that summarizes your findings in words for a non-technical reader. It should explain the problem being examined from an economic perspective, i.e. it should motivate interest in the issue on the part of the reader. Your report should explain how you are investigating the issue, in simple language. It should explain why you are approaching the problem in this particular fashion. Your executive report should explain the economic importance of your findings.The technical details of your findings you can attach as an appendix.II. The EXCEL data file carpoll contains information on three dependent categorical variables on preferences towards vehicles: type, size and country of manufacture. This data is a sample file in JMP. There are 303 observations in the poll, obtained in a given geographical area. The dependent variable “type” has three categories: family, sporty, and work. The variable “size” also has three categories: large, medium, and small. The variable “country of manufacture” also has three categories: American, European, Japanese.There are three explanatory variables in the data file. The first is a quantitative variable age. The second is an independent categorical variable, gender, which can be coded as a dummy variable, male equals one and female equals zero. The third explanatory variable is also a categorical variable, married or single which can be coded as a dummy variable, married equals one and single equals zeroNov. 7, 2006 ECON 240A-2 L. PhillipsTake-home I : Tuesday Nov. 21A. Consider two categories for the variable type of vehicle: family equals one, and other equals zero. 1. Use EXCEL to plot the zero/one categorical variable “family-type” vehicle against the quantitative variable age. Add a linear fit to the points.a. Is the relationship between the probability of favoring a family type vehicle and age positive or negative? b. What is the linear regression fit approximating?2. Use EViews to estimate a linear probability model for type of vehicle, i.e.family yes/no as explained by age, gender and maritalstatus, coded as explained above.a. Which explanatory variables are significant and do they have a positive or negative impact on the probability of desiring a family type car?b. How much does the marital status of married increase the probability of favoring a family type car for a given age?c. Use Eviews to plot the fitted or estimated probability of favoring a family type car against age. i.Why are there four lines in the plot?Nov. 7, 2006 ECON 240A-3 L. PhillipsTake-home I : Tuesday Nov. 21ii. At approximately what age do married women begin to favor a family type vehicle?iii. At approximately what age do single men begin to favor a family type vehicle?iv. Explain how this result affects advertising on TVfor different types of vehicles by demographic group?3. Use EViews to estimate a logit probability model for type of vehicle, i.e. family yes/no as explained by age, gender and marital status, coded as explained above.a. Does this estimated logit model do a better job of predicting those who favor a family type car or those who do
View Full Document
Unlocking...