Professional Documents
Culture Documents
Statsmidterm 01 Key
Statsmidterm 01 Key
Statsmidterm 01 Key
X = 52.17
Med = 50
Mode = 50
3. [2 points] Find the sample variance and standard deviation.
s X2 = 75.61
s X = 8.70
4. [3 points] What percentage of the observations fall within two standard deviations of
the mean? Comment (i.e., say something about the distribution of the data and offer
some supporting evidence without actually graphing the relative frequency
distribution).
A
A
F
0.45
0.25
0.70
F
0.05
0.25
0.30
0.50
0.50
1.00
P ( AF ) 0.05
=
= 0.17
P (F ) 0.30
P( AF ) 0.45
=
= 0.90
P ( A)
0.50
(b) [1 point] What is the probability of a request for additional information given that
the bid will ultimately be successful?
P ( B | A) = 0.75
(c) [3 points] What is the probability that the bid will be successful given a request
for additional information?
P( A | B) =
P ( A) P ( B | A)
(0.50)(0.75)
=
= 0.652
P ( A) P( B | A) + P ( A ) P ( B | A ) (0.50)(0.75) + (0.50)(0.40)
8. [4 points] The unemployment rate in April 2003 was 5.8% (source: Bureau of Labor
Statistics). Suppose that 100 employable people are selected randomly. What is the
probability that at least 4 are unemployed? Use the binomial distribution to compute
the exact probability and then compute the Poisson approximation.
Binomial:
P( X 4) = 1 (P( X = 3) + P( X = 2) + P( X = 1) + P( X = 0) )
= 1 0.1617997 = 0.8382
Poisson:
P( X 4) = 1 (P( X = 3) + P( X = 2) + P( X = 1) + P( X = 0) )
1 0.1699639 = 0.8300
9. [4 points] Suppose that the percentage of returns for a given year for all stocks listed
on the New York Stock Exchange are normally distributed with a mean ( X ) of 12.4
percent and a standard deviation ( X ) of 20.6 percent. Consider drawing a random
sample of n = 5 stocks from the population of all stocks and calculating the mean
return ( X ) of the sampled stocks. Find the interval containing 95.44 percent of all
possible sample mean returns.
X will have a normal distribution regardless of sample size because X is
normally distributed (Central Limit Theorem). Using z, the standard normal,
we can see that 95.44% of all values are within 2 standard deviations.
20.6
12.4 2
[ 6.03, 30.83]
5
10. Assume that you have a population with a mean X = 3.2 and variance X2 = 2 .
(a) [3 points] Describe the most important features of the sampling distribution of the
sample mean ( X ).
According to the CLT, the distribution of X will be normal with
2
X = X = 3.2 and X = X =
regardless of the distribution of X, as
n
n
long as sample size is large ( n 25 ).
(b) [3 points] Will the shape of the population distribution affect your answer to part
(a)? Will the size of the sample affect your answer to part (a)? Explain.
The shape of the population distribution only affects the answer in (a) if
sample size is small ( n < 25 ). The only way to ensure that X will be normal
with smaller sample sizes ( 10 < n < 25) is if X has a symmetrical distribution.
With very small sample sizes ( n < 10 ), the only way to ensure that X will be
normal is if X is also normal.
11. In 2002, the mean ( X ) tuition cost at state universities throughout the United States
was $4260 per year (St. Petersburg Times, December 11, 2002). Assume the
standard deviation ( X ) was $900 and that a random sample of 50 universities was
selected.
(a) [3 points] What is the probability that the simple random sample will provide a
sample mean greater than $4500?
4500 4260
P (X > 4500) = P z >
= P( z > 1.89) = 0.5000 0.4706 = 0.0294
900
50
(b) [3 points] Do you think the probability of randomly drawing a single university
with tuition greater than $4500 would be greater or less than the probability found
in part (a)? Explain your logic without calculating.
900 2
compared to
50
900 2 . Therefore, extreme values are more likely when randomly selecting
one observation rather than numerous and taking an average.
The probability would be greater. X has less variance -
(c) [3 points] Is there any way to calculate the exact probability for part (b)? If so,
find the probability and explain the legitimacy of your procedure.
Yes, but since the calculation relies on using the standard normal
distribution, the distribution of X must be normal. The problem does not
specify this, so it would have to be assumed in order to perform the following
calculation.
4500 4260