the following questions for each data set: 1) Are the variables cross section or time series data? 2) How do you imagine that the data were collected? 3) Is the sample size sufficient to yield a good estimate? Does it fulfill Doane's Rule or Evan's Rule? 4) State you hypothesis about the sign of the slope for each predictor variable. 5) Generate a correlation matrix for your predictors. Based on the matrix is collinearity a problem? 6) Run the regression in Megastat requesting VIF's. Do they suggest a problem? 7) Interpret the slope coefficient. Does the intercept have meaning given the range of the data? 8) Use Megastat to fit the regression model, including residuals and standardized residuals 9) Interpret the P-value for each slope coefficient 10) Interpret the R^2 value 11) Study the table of residuals. Identify outliers, and unusual observations (standardized obs. that exceed 3, and 2 std. deviations respectively). 12) Output a normal probability plot. Do you see evidence that your regression violates the assumption of normality? 13) Inspect the residual plot to check for heteroscedasticity. Report your conclusions. 14) Identify any observations with high leverage