Business Statistics: Communicating with Numbers
By Sanjiv Jaggia and Alison Kelly
McGraw-Hill/Irwin Copyright © 2013 by The McGraw-Hill Companies, Inc. All rights reserved.
Chapter 11 Learning Objectives (LOs)
11-2
Assessing the Risk of Mutual Fund Returns
In Chapter 3, we examined annual return data
for Vanguard’s Metals fund and Fidelity’s
Income fund.
The mean return evaluates reward.
The standard deviation assesses risk.
11-3
Assessing the Risk of Mutual Fund Returns
1. Evaluate the investment risks of the funds by
constructing confidence intervals for the
standard deviations.
2. Implement tests to verify if the investment
risks of the funds deviate from specific values.
3. Determine if the risk of the Metals fund is
significantly greater than the risk of the
Income fund.
11-4
11.1 Inference Concerning the Population Variance
LO 11.1 Discuss features of the χ2 distribution.
11-5
LO 11.1 The Sampling Distribution of S2
11-6
LO 11.1 The Chi-Square Distribution
11-7
LO 11.1 Locating Chi-Square Values
11-8
LO 11.1 The Chi-Square Table
11-9
LO 11.1 Left-tail Values
11-10
LO 11.1 Graph of right and left values
11-11
LO 11.2 Construct a confidence interval for the population variance.
11-12
LO 11.2 Example 11.2
11-13
LO 11.2 Example 11.2 (continued)
For the Metals fund, the 95% confidence
interval for the population standard deviation
is 25.54 ≤ σ ≤ 67.79.
For the Income fund, the standard deviation
s = 11.07. What is a 95% confidence
interval estimate of the population variance?
11-14
Hypothesis Test About σ2
LO 11.3 Conduct a hypothesis test for the population variance.
11-15
LO 11.3 Example 11.3
11-16
LO 11.3 Example 11.3 (continued)
11-17
LO 11.3 Example 11.4
11-18
LO 11.3 Example 11.4 (continued)
We use Excel’s function CHISQ.DIST.RT to get an
exact p-value.
Because it was a two-tailed test, the p-value is
2(.0838) = 0.1676.
11-19
LO 11.3 Example 11.4 (continued)
Since the p-value = 0.1676 > 0.05 = α,
we do not reject H0.
At the 5% significance level, we cannot
conclude that the population standard
deviation differs from 8.5%.
11-20
11.2 Inference Concerning the Ratio of Two
Population Variances
LO 11.4 Discuss features of the F distribution.
11-21
LO 11.4
11-22
LO 11.4 The F Distribution
11-23
LO 11.4 Right-tail Values
With df1 = 6 and df2 = 8, 5% of the area falls
above 3.58.
11-24
LO 11.4 Left-tail values
11-25
LO
11.5 Construct a confidence interval for the ratio of two population variances.
11-26
LO 11.5 Example 11.6
Section Sample size Sample Variance
Section 1 11 182.25
Section 2 16 457.96
11-27
LO 11.6 Conduct a hypothesis test for the ratio of two population variances.
11-28
LO 11.6 Example 11.7
Section Sample size Sample SD Sample Variance
Section 1 11 13.5 182.25
Section 2 16 21.4 457.96
11-29
LO 11.6 One-Tailed F-test
We specify one-tailed tests as right-tailed tests;
that is, we place the larger sample variance in the
numerator when calculating the value of the test
statistic.
It is easier to find the critical value on the right
side of the F distribution.
11-30
LO 11.6 Example 11.8
Mutual fund: Metals Income
Mean 24.65% 8.51%
Standard Deviation 37.13% 11.07%
11-31
LO 11.6 Example 11.8 (continued)
11-32
LO 11.6 Using Excel
If we have the raw data, Excel’s F.TEST function
calculates the p-value.
This always assumes a two-tailed test. To get the one-
tailed version, compute the p-value as 0.0013 / 2 =
0.0007.
11-33
Synopsis of Introductory Case
95% confidence intervals of the Metals fund and
the Income fund show that the risk of the funds
differ. At the 5% significance level, the risk of the
Metals fund is greater than the risk of the Income
fund.
At the 5% significance level, the standard deviation
of the Metals fund exceeds 25%.
At the 5% significance level, the standard deviation
of the Income fund does not differ from 8.5%.
11-34
