1. Do you prefer confidence interval estimation or point estimation for the unknown population mean? why?
2. Do you think hypothesis testing is useful in business? Why or why not?
3. How would you interpret the relationship between two numeric variables when the estimated least squares regression line for them is essentially horizontal (i.e. flat)?
4. Suppose you want to investigate the relationship between a dependent variable Y and two potential independent variables X1 and X2. Is the R-square value for the equation with both X variables included necessarily at least as large as the R-square value form each equation with only a single X? Explain why or why not. Could the R-square for the equation with both X variables included be larger than the sum of the R-square values from the separate equations, each with only a single X included?