1/26/2011

Return to Simple Linear Regression - (see Chapter2-Inference.PPT)

• Inferences about the slope of the population regression line
• Confidence intervals
• Hypothsis tests
• Inference for the population correlation coefficient

Class Activity on Robbery Rates

• A criminologist studying the relationship between population density and robbery rate in medium-sized U.S. cities collected the data for a random sample of 16 cities. The data for X = population density of the city (number of people per unit area) and Y = the robbery rate last year (number of robberies per 100,000 people) can be found in robbery.dat.
  • Obtain the estimated regression line. Plot the estimated regression line and the data. Does the simple linear regression model appear to provide a good fit?
  • Obtain point estimates of the following:
    • the difference in the mean robbery rate in cities that differ by one unit in population density
    • the mean robbery rate last year in cities with population density X = 60
    • the random error term for the 10th observation
    • the variance of the error terms

Please read Sections 2.4 and 2.5 for class on Friday.