3. Refer to the Lincolnville School District bus data. Consider a regression a) In addition...
90.2K
Verified Solution
Link Copied!
Question
Accounting
3. Refer to the Lincolnville School District bus data. Consider a regression
a) In addition to the engine dummy variable construct manufacturer dummy variables. (Hint: Since there are 3 manufacturers, you need 2 dummy variables. One takes a value of 1 if the manufacturer is Keiser and 0 if the
manufacturer is Thompson or Bluebird and a second takes a value of 1 if the manufacturer is Thompson and 0 if the manufacturer is Keiser or Bluebird. Note: Having 3 dummies for 3 manufacturers would create multicollinearity.)
b) Suppose you are considering a regression where maintenance cost is the dependent variable and the potential independent variables are manufacturer (both dummy variables, engine type, age, odometer miles, and capacity.) Create a correlation matrix. Are there any
variables you think cannot be in a regression together? c) Use a statistical software package to determine the
multiple regression equation. (Use your conclusions from the correlation matrix to omit independent variables, if necessary.)
d) Show that your regression equation shows a significant relationship (i.e. we can reject the null that all coefficients are 0.)
e) Write out the regression equation and interpret its practical application.
f) Report and interpret the R-square.
g) Develop a histogram of the residuals from the final
regression equation. Is it reasonable to conclude that
the normality assumption has been met?
h) Plot the residuals against the fitted values of Y from the
final regression equation. Plot the residuals on the vertical axis and the fitted values on the horizontal axis. Use the graph to explain whether you think the linearity and homoskedasticity assumptions hold