STA 6126 – Fall 2006 – Exam 4
Print Name ____________________
UFID _________________
I have not cheated on this exam. ________________
The slope of the least squares prediction equation and the Pearson correlation coefficient are similar in the sense that
(Circle any that are True):
•
They do not depend on the units of measurement
•
They both must fall between 1 and +1
•
They both have the same sign
•
They both have the same
t
staistic value for testing H
0
: Independence
One can interpret
r
= 0.40 as (Circle any that are True):
•
A 16% reduction in (total squared) error occurs when using
X
to predict
Y
as opposed to using
Y
to
predict
Y
•
A 40% reduction in (total squared) error occurs when using
X
to predict
Y
as opposed to using
Y
to predict
Y
•
16% of the time
Y
Y
=
^
•
Y
changes on average, by an estimated 0.40 units, for a oneunit increase in
X
•
When
X
is used to predict
Y
, the “typical” residual is 0.40.
You find the following partial ANOVA table in the grad student computer lab in your department. Unfortunately,
someone spilled coffee on it, and some values are unreadable. Complete the table from a simple linear regression
model.
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 '08
 YESILCAY
 Correlation, Correlation Coefficient, Least Squares, Regression Analysis, researcher, linear regression model

Click to edit the document details