Stat 160 Prequiz over Section 1.10
This work is to be submitted for credit. Attempt all problems. Make sure you have attempted all problems before you submit. You may solve the problems several times, but only the first submission will get credit.
Please fill out the information below.
Your User Name:
Your Password:
1. Which of the following is a measure of the relationship between two variables?
The sample interquartile range.
The Hodges-Lehmann estimate.
The sample range.
The sample correlation coefficient.
2. Which of the following is
not
true about the correlation coefficient?
It measures the linear relationship between two variables.
It is computed using the sample covariance and the standard deviations of the two variables.
It always takes values between -1 and 1.
It has the value 1 if there is a perfect circular relationship between the two variables.
3. Suppose we fit the linear model
Y = a + bX + e
using the least squares technique. What does
R
^{2}
= .80
mean?
We have accounted for 80% of the variation in
Y
.
We have accounted for 20% of the variation in
Y
.
The value of the slope parameter is .80.
It has no practical meaning.
4. What is one advantage of using
R
_{W}
^{2}
(which corresponds to the Wilcoxon fit) instead of
R
^{2}
?
R
_{W}
^{2}
is simpler to compute as compared to
R
^{2}
.
R
_{W}
^{2}
is always greater than
R
^{2}
.
R
_{W}
^{2}
is always less than
R
^{2}
.
R
_{W}
^{2}
is less sensitive to outliers than
R
^{2}
.