Applied Managerial Statistics
Final Project
Bryant/Smith Manual Case 7:
Tom’s Used Mustangs
Applied Managerial Statistics
I. Executive Summary
The data file named “MUSTANGS”, contains observations on 35 used Mustangs with a variation of 10 different characteristics[1]. This file was used to prepare a report on the influence of various options on asking price and to relay how this information could be used to set prices on used Mustangs. Statistical analysis by Hypothesis Testing and Multiple Regression Analysis was performed on the asking prices for used Mustangs and it was found that there are five independent variables that affect the selling price of used Mustangs:
• If the car is a convertible or not • If the car is a GT model or not • Age of the car in years • Odometer reading in miles • Number of cylinders in the engine
II. Introduction
Research suggests that pricing strategies can have a huge influence on company profits.[2] Several customers of Tom’s Used Mustangs have mentioned that asking prices are way out of line with the rest of the market. These prices may be too high or too low, and are never close to the going rate. It had been determined that asking prices for the used Mustangs were based on an informal scheme and has not proved to be as effective as anticipated.
In researching competitors, and because the physical characteristics are many, there has been some difficulty pinpointing a useful pricing strategy. To effectively find a pricing scheme, statistical analysis of the given data involved hypothesis testing and multiple-regression analysis. Hypothesis testing is the rational agenda for applying statistical tests. The main question we usually wish to dig up from a test such as this is whether the sample data is important or not. There are two hypotheses that are possible:
• H0: the null hypothesis. The number is from a standard normal distribution with μ = 0. • HA: the
Bryant/Smith Manual Case 7:
Tom’s Used Mustangs
Applied Managerial Statistics
I. Executive Summary
The data file named “MUSTANGS”, contains observations on 35 used Mustangs with a variation of 10 different characteristics[1]. This file was used to prepare a report on the influence of various options on asking price and to relay how this information could be used to set prices on used Mustangs. Statistical analysis by Hypothesis Testing and Multiple Regression Analysis was performed on the asking prices for used Mustangs and it was found that there are five independent variables that affect the selling price of used Mustangs:
• If the car is a convertible or not • If the car is a GT model or not • Age of the car in years • Odometer reading in miles • Number of cylinders in the engine
II. Introduction
Research suggests that pricing strategies can have a huge influence on company profits.[2] Several customers of Tom’s Used Mustangs have mentioned that asking prices are way out of line with the rest of the market. These prices may be too high or too low, and are never close to the going rate. It had been determined that asking prices for the used Mustangs were based on an informal scheme and has not proved to be as effective as anticipated.
In researching competitors, and because the physical characteristics are many, there has been some difficulty pinpointing a useful pricing strategy. To effectively find a pricing scheme, statistical analysis of the given data involved hypothesis testing and multiple-regression analysis. Hypothesis testing is the rational agenda for applying statistical tests. The main question we usually wish to dig up from a test such as this is whether the sample data is important or not. There are two hypotheses that are possible:
• H0: the null hypothesis. The number is from a standard normal distribution with μ = 0. • HA: the
References: VI. Appendix ----------------------- [1] Bryant-Smith: Practical Data Analysis, Volume I, Second Edition. Tom’s Used Mustangs [2] http://knowledge.wharton.upenn.edu/article.cfm?articleid=792. 06/04/2003. [3] http://www.webpages.uidaho.edu/~brian/why_significance_is_five_percent.pdf