Covariance+and+Correlation

Covariance and Correlation (Distribution Theory) (GWU EMSE-271)
Index | Topics (Logical Lectures) | Lectures | Problems | Readings | References

"In [|probability theory] and [|statistics], **covariance** is a measure of how much two variables change together . . " - [|Wikipedia]

Covariance is greater than zero when the variables are not independent. [One can say "When large values of X tend to be associated with large values of Y and vice versa, X and Y are said to be positively dependent." (EMSE 271, Fall 2009 Slide 44).

"The correlation between two random variables X and Y is defined" in terms of the covariance of XY divided by their variances. EMSE 271, Fall 2009 Slide 44)

"Correlation is the "(standard) "measure of linear dependence;" from -1 to 1. EMSE 271, Fall 2009 (Slide 45). ** Zero does not indicate no dependence; merely no linear dependence. ** - Mazzuchi.

In regression analysis (Session 9). "the covariance matrix of bHat is used in making "inferences about the values of the regression parameters." EMSE 271, Fall 2009

COMMON QUESTION: ...


 * Sources:**
 * EMSE 271, Fall 2009 (Slides 43-45)
 * EMSE 280, Spring 2009
 * Covariance. (2009, April 10). In //Wikipedia, The Free Encyclopedia//. Retrieved 17:08, April 30, 2009, from []