PROJECT STAT 201 Dr. Esteban Walker
Fall 2002
You may complete this two-phase project either individually or as a member of a group of up to four students. A list of the members of each group is due Sept. 24.
The data for this project contains information on each household in Spring City, a small city in the midwest. The data are available by clicking here.
The data base contains the following information on each of the 6063 households in Spring City:
PHASE I (Due Oct. 8)
1. Using EXCEL select a simple random sample of 100 households from each sector for a total of 400 households (EXCEL will give you the household numbers and you will have to retreive the information from the frame). Your report should contain the list of the elements in your sample along with an explanation of the procedure used to generate the random numbers.
The rest of the project is based on the sample of 400 households that you selected.
2. Carry out the following tasks:
- For the quantitative variables calculate measures of location and dispersion. Also construct histograms to explore the distribution of each variable (For all 400 observations and also per sector).
- Do a) above (except for the histograms) for the two groups defined by X2 (for all 400 observations).
- Construct a contingency table with X2 and X4 (for all 400 observations).
An executive report should be written summarizing the main finding of the study. It must be typed and directed to the Mayor of Spring City, who is paying for your services. Explain in practical terms your findings, including graphs and tables.
The number of points in this phase is 40. Exceptional reports can earn a maximum of 5 bonus points. Criteria to award bonus points include: clarity of presentation, good organization (divided into sections?), good graphs (well documented), neatness of the manuscript, spelling, grammar.
The graded report will be returned to you so that phase II can be completed. No reports will be accepted after the beginning of class on Oct. 8.
PHASE II (Due Nov. 19)
1. Explore the relationship between
- Family size and monthly housing expenditure
- Monthly utility bill and family income
- Monthly housing expenditure and family income
Use scatterplots, regression analysis (including residual plots), and correlation. For bonus points do the analysis for each of the four sectors of Fall City
2. Construct and interpret confidence intervals for the following parameters:
- Average family income
- Proportion of households with second income
- Average family size
3. Answer the following questions based on the sample information at a significance level of
a = .05:
- Is the average family income for Sector 1 less than $40,000?
- Is the proportion of households with a second income (in the whole city) greater than 65%?
4. Determine whether the regression models used in 1 above are useful. Use a significance level of .10.
An executive final report should be written. It should be addressed to the Major of Spring City and must include the following:
- Introduction and statement of purpose
- Summary and explanation of the main findings of the study
- Conclusions
Keep in mind that the final report is about both phases. If some of the results of phase I are relevant to those of phase II, make the connection.
Your report should be typed. The number of points for the final report is 40. A maximum of 5 bonus points can be earned by exceptional reports. The criteria for bonus points is the same as above. No reports will be accepted after the beginning of class on Nov. 19.