Homework 4
Turn in all of the following homework problems on Thurs Oct 28 (for
Foster's section, Monday Nov 1st).
- As personnel manager for Computeronics Inc. you may receive
many applications from people who want jobs as systems
programmers. You first have to decide whether or not an
applicant should go through a thorough screening test which
costs the company $100. There are two reasons why an applicant
should not be given the screening test: you are confident that
he/she is qualified, in which case you will hire the applicant,
or you are confident that he/she is unqualified, in which case
you will not hire the applicant. If you hire an applicant, and
he/she is qualified it is worth $800 to the
company. On the other hand, if an applicant is
unqualified and you hire the applicant the company estimates
their loss to be $300 for low quality work. Finally, they gain/lose
nothing if they do not hire the applicant.
From past experience, the test accuracy is summarized as
follows:
- if an applicant is qualified, the probability that an
applicant will pass the test is .9
- if an applicant is unqualified, the probability that an
applicant will fail the test is .9
An applicant sends his resume to you and you feel that there is
a .5 chance that he is qualified.
- Set up a decision tree starting with the decision as to
whether or not the applicant should be given the screen
test.
- Should you give the applicant the screen test? What is
the best strategy?
- What is the expected value of prefect information prior
to the screen test?
- How much is the screen test worth?
- What other factors should you consider that are not
included in the above analysis?
- Do the following problems:
- Text exercise 4.50 (page 153)
- Text exercise 4.51 (page 154)
- Text exercise 4.52 (page 154)
- Text exercise 4.56 (page 161)
- Text exercise 4.57 (page 161)
- Text exercise 4.58 (page 161)
- Text exercise 4.59 (page 161)
- Do the following problems:
- Text exercise 4.104 (page 176)
- Text exercise 4.105 (page 177)
- What are the mean and standard deviation for the total
number of repairs made for number of motor/transmission
repairs and number of body repairs?
- Here are summary statistics on monthly returns for five US
common stocks, based on 60 observations from January, 1991,
through December, 1995:
Company | Bristol Myers | Ford | IBM | Merck | USAir |
mean | 0.017 | 0.019 | 0.0025 | 0.0088 | 0.0097 |
Std. Dev. | .062 | 0.077 | 0.081 | 0.050 | 0.16 |
Here is the correlations matrix:
Company | Bristol Myers | Ford | IBM | Merck | USAir |
Bristol Myers | 1.0 | 0.12 | 0.02 | 0.09 | 0.20 |
Ford | 0.12 | 1.0 | 0.27 | 0.04 | -0.01 |
IBM | 0.02 | 0.27 | 1.0 | 0.66 | 0.22 |
Merck | 0.09 | 0.04 | 0.66 | 1.0 | 0.21 |
USAir | 0.20 | -0.01 | 0.22 | 0.21 | 1.0 |
Assume that these summary figures will still apply to future
investments. Also assume that you may not make negative
investments (such as short sales) in any of the stocks.
- What portfolio (expressed as fractions of a dollar
invested in each of the five stocks) would yield the
highest expected return? (Hint: This is easy.)
- What stock is the riskiest? Is it true that a
portfolio with half the money invested in this stock
and half invested in one of the other stocks will be
riskier than a portfolio with all the money invested
in the other stock?
- What pair of stocks have the highest covariance (not
necessarily the highest correlation)? What pair of
stocks have the lowest covariance?
- Consider two portfolios, one with equal amounts
invested in the two highest-covariance stocks, the
other with equal amounts invested in the two
lowest-covariance stocks. Find the expected returns
and standard deviations (per dollar invested) in each
portfolio.
Last modified: Wed Oct 13 09:44:55 EDT 1999