Lesson 9 - Ch9: Regression Stat113 Correlation Weve seen...

Info iconThis preview shows pages 1–6. Sign up to view the full content.

View Full Document Right Arrow Icon
Ch9: Regression Stat113
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Correlation We’ve seen that correlation measures the linear relationship between two variables In what direction? (pos. or neg.) How strong? (close to 1, or to -1) When two variables are strongly correlated, if we know an individuals value for one variable, this can help us to predict their value for the other variable
Background image of page 2
Sample Situation Consider two variables with a strong, positive correlation Boats registered at a given marina in florida Manatee Kills at a given marina in florida Our individuals are marinas, and for each marina, for a ten year period, we have recorded the total number of motor boats that have ever been registered there, as well as the total number of manatees that have died there.
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Simplified Version Pearson Product-Moment Correlation No Selector   kills boats kills 1.000 0.912 boats 1.000 From DataDesk, we can view a data table by double clicking the variables, and a correlation table (Calc > Correlations > Pearson Product- Moment). Result: Correlation is Strong, Positive We might say: We can predict manatee deaths that have occurred in some other marina, whose manatee deaths we haven’t kept track of, in the following way: If the new marina has a value for Boats which is greater than the mean, by S standard deviations, then it’s value for Kills will be that many standard deviations above the mean of Kills .
Background image of page 4
Contd… Suppose we get data for a new marina: Boats : 705 We want to predict Kills , so we must calculate the mean and standard deviation for both variables (Calc > Summaries > Reports) » 705 is about one standard deviation above the mean of Boats : (705 - 601.544)/103.832 ≈ 1 » 1 standard deviation (of Kills ) above the mean of Kills would be: 32.6111 + 12.8161 ≈ 45 » So using this model, we could expect there to have been about 45 Kills at this marina, for which we previously had no data.
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 6
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 02/15/2011 for the course STATISTICS 113 taught by Professor Cassidy during the Fall '10 term at CUNY Hunter.

Page1 / 21

Lesson 9 - Ch9: Regression Stat113 Correlation Weve seen...

This preview shows document pages 1 - 6. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online