Basic HTML Version
Q
uantitative
R
easoning &
P
roblem
S
olving
342
© 2014 Pacific Crest
●
The correlation is not linear
Example
:
0
Variable 2
Variable 1
7 6 5
3 2 1
8 9 10
4
0
8
7
6
5
4
3
2
1
10
9
Why?
The mean of both
x
and
y
is approximately 5.5 and the regression line would be flat
going through that point. This gives no real value in predicting because no matter
what
x
value you use, the predicted result is 5.5.
●
The correlation is not strong
Example
:
0
20
40
60
80
100
120
1000 1500 2000 2500 3000 3500 4000 4500 5000
Why?
There is virtually no correlation between
x
and
y
; the relationship actually appears to
be random. Remember that for a linear regression model to be useful, the correlation
coefficient,
r,
should be relatively close to 1 or -1. In this case, the value of
r
is 0.03,
showing that there is a very low degree of correlation.