- We are only considering LINEAR relationships
- r and least squares regression are NOT resistant to outliers
- There may be variables other than x which are not studied, yet do influence the response
variable
- A strong correlation does NOT imply cause and effect relationship
- Extrapolation is dangerous.
Dr. Christina Hayes
Wilson 2-263
Department of Mathematical Sciences
Montana State University
Bozeman, MT 59717
phone: 406-994-6557
fax: 406-994-1789
christina.hayes@montana.edu
(Email will likely reach me faster than a phone call)