Each month, the U.S. Census Bureau selects a random sample of about 300,000 U.S. households to participate in the American Community Survey (ACS). The chosen households are notified by mail and invited to complete the survey online. The Census Bureau follows up on any uncompleted surveys by phone or in person. Data from the ACS are used to determine how the federal government allocates over $400 billion in funding for local communities.

The file acs survey ch1 project.xls, which can be accessed from the book’s website at highschool.bfwpub.com/tps6e, contains data for 3000 randomly selected households in one month’s ACS survey. Download the file to a computer for further analysis using the application specified by your teacher.

Each row in the spreadsheet describes a household. A serial number that identifies the household is in the first column. The other columns contain values of several variables. See the code sheet on the book’s website for details on how each variable is recorded. Note that all the categorical variables have been coded to have numerical values in the spreadsheet.

Use the files provided to answer the following questions.

1. How many variables are recorded? Classify each one as categorical or quantitative.

2. Examine the distribution of location (division or region) for the households in the sample. Make a bar graph to display the data. Then calculate numerical summaries (counts, percents, or proportions). Describe what you see.

3. Explore the relationship between two categorical variables of interest to you. Summarize the data in a two-way table. Then calculate appropriate conditional relative frequencies and make a side-by-side or segmented bar graph. Write a few sentences comparing the distributions.

4. Analyze the distribution of household income (HINCP) using appropriate graphs and numerical summaries.

5. Compare the distribution of a quantitative variable that interests you in two or more groups. For instance, you might compare the distribution of number of people in a family (NPF) by region. Make appropriate graphs and calculate numerical summaries. Then write a few sentences comparing the distributions.