3/8/11
•
Regression 1
o
The point of Regression
Correlation is very close cousin to regressions
With correlations we wanted to determine the strength and
direction of the relationship between two variables
With regression we want to predict the value of one variable from
another
We can also use more than one predictor so we can examine how a
number of different variables predict an outcome
o
Predicting One Variable from Another
Knowing one measure gives information about others from same
subject
•
Knowing weight tells us height
Goal: Come up with a rule or function that uses X to compute Y
Y hat predicted value of Y
•
Function of X
•
Best prediction of Y based on X
o
How Good is Prediction
Error= YY(hat)
Goal Keep error close to zero
•
Minimize Mean squared error
o
MSE=Sum of (YYhat)^2/n1
o
Properties of Correlation
Measures relationship between two continuous variables
•
How well data are fit by a straight line
•
R=sum of z sub x times z sub y/n1
This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
This is the end of the preview.
Sign up
to
access the rest of the document.
 Spring '11
 Worthy
 Regression Analysis, multiple predictor variables

Click to edit the document details