File: Open Data Table:  residuals.JMP

Basic: Bivariate:  Y1 and X
 Hot spot: Fit Line
  - note statistical significance and high R-square 
 Hot spot (of Linear Fit): Plot Residuals
  - very good residuals

Basic: Bivariate:  Y2 and X
 Hot spot: Fit Line
  - note statistical significance and reasonably high R-square 
 Hot spot (of Linear Fit): Plot Residuals
  - note curve, not a linear fit

Basic: Bivariate:  Y3 and X
 Hot spot: Fit Line
  - note statistical significance but lower R-square 
 Hot spot (of Linear Fit): Plot Residuals
  - increasing variance (heteroscedasticity)

Basic: Bivariate:  Y4 and X
 Hot spot: Fit Line
  - note statistical significance and reasonably high R-square 
 Hot spot (of Linear Fit): Plot Residuals
  - statistical significance, but such a low R-square that may not 
      be useful in practice


File: Open Data Table:  storks.txt
Basic: Bivariate:  storks are "X", people are "Y"
 Hot spot: Fit Line
  - statistical significance and high R-square 
 Hot spot (of Linear Fit): Plot Residuals
  - residuals look good, although sample size is small


File: Open Data Table:  quiz.txt
Basic: Bivariate:  QuizTotal is "X", Midterm.Grade is "Y"
 Hot spot: Fit Line
  - statistical significance with somewhat low R-square 
 Hot spot (of Linear Fit): Plot Residuals
  - residuals pretty good
  - possible slight decreasing variability?


File: Open Data Table:  o-ring.txt
Basic: Bivariate:  Temperature is "X", Damage is "Y"
 Hot spot: Fit Line
  - statistical significance with moderate R-square 
 Hot spot (of Linear Fit): Plot Residuals
  - note edge effects (damage can't be negative)