STA215H5 Lecture 12: Regression residuals, outliers, influential points, extrapolation

75 views2 pages
8 Feb 2017
School
Department
Course
Professor

Document Summary

Human error can be a possibility because the data is being inputted by a human. If you have an outlier that is really random, you can ignore it and explain where it came form or how it occurred. Fit 2 lines of best fit with and without the outlier and then explain why there might be an outlier. When you have a cluster, there is no line. When you add a random outlier, a line can be drawn. Leverage: talks about an outlier whose x-value is far from the other x-values. Influential value: when you omit the outlier, you can have a very different line of best fit. 2 things that can happen when you have an outlier. You cannot delete an error, if you can find a reason why the outlier is like that, then you can remove it.

Get access

Grade+20% off
$8 USD/m$10 USD/m
Billed $96 USD annually
Grade+
Homework Help
Study Guides
Textbook Solutions
Class Notes
Textbook Notes
Booster Class
40 Verified Answers
Class+
$8 USD/m
Billed $96 USD annually
Class+
Homework Help
Study Guides
Textbook Solutions
Class Notes
Textbook Notes
Booster Class
30 Verified Answers

Related Documents

Related Questions