Assignment 1 (individual) 60 points
Note: alpha=0.05 unless mentioned otherwise
Please review our course syllabus for the submission deadline and format requirement!
1. During periods of high electricity demand, especially during the hot summer months, the
power output from a gas turbine engine can drop dramatically. One way to counter this
drop in power is by cooling the inlet air to the gas turbine. An increasingly popular
cooling method uses high pressure inlet fogging. The performance of a sample of 67 gas
turbines augmented with high-pressure inlet fogging was investigated by the Journal of
Gas Turbines. One measure of performance is heat rate (in kilojoules per kilowatt per
hour). Heat rates for the 67 gas turbines are provided in the file GASTURBINE.sav.
Suppose that a standard gas turbine has on average, a heat rate of 10,000 kj/kwh.
Conduct a test to determine if the mean heat rate of gas turbines augmented with high-
pressure inlet fogging exceeds 10,000 kJ/kWh. Do not forget to state the hypothesis.
15 points
Answer:
The hypothesis can be expressed as –
H0: <= 10,000 (The mean heat rate of gas turbines is less than equal to 10,000 kJ/kWh)
Ha: > 10,000 (The mean heat rate of gas turbines exceeds 10,000 kJ/kWh)
= 0.05
Where is the mean heat rate of gas turbines.
In order to test the above hypothesis, we run a one-sample t-test in the SPSS on the data and
compare the mean heat rate with 10,000. The SPSS output is provided below –
One-Sample Statistics
N Mean Std. Deviation Std. Error Mean
HEATRATE 67 11066.43 1594.960 194.855
One-Sample Test
Test Value = 10000
95% Confidence Interval of
Significance the Difference
One- Two- Mean
t df Sided p Sided p Difference Lower Upper
HEATRATE 5.473 66 <.001 <.001 1066.433 677.39 1455.47
Comparing the p value which is < .001 to the alpha = 0.05 significance level, we can see that the
p value is less than alpha. Hence, the null hypothesis is rejected. Which means, the heat
rate of the gas turbines does exceed 10,000 kJ/kWh.
2. The CEO of Kohl’s is interested in understanding whether the average store sales for the
stores in the east coast are significantly different from those in the west coast. The CEO
suspects that since the company has been advertising more in the east coast, the east coast
sales would be higher than those in the west coast. In order to test his hypothesis, the
CEO asks his secretary to randomly pick 10 stores each in the east and west coasts and
record their average monthly sales for the past year(in thousands of dollars). The data is
in eastwest.sav (data set is provided in the D2L content area in Module 3, Assessment
section). State the appropriate hypothesis, run the appropriate test using SPSS and
provide interpretation. 15 points
Answer:
The hypothesis can be expressed as –
H0: 2 - 1 <= 0
Ha: 2 - 1 > 0
= 0.05
Where 1 is the mean sales of the stores in the west coast and,
2 is the mean sales of the stores in the east coast.
The research hypothesis is that the sales for the stores in the east coast is higher than stores in the
west coast. Hence, 2 should be greater than 1. This is stated as the alternate hypothesis.
The opposite is stated as the null hypothesis.
We use an independent sample t-test (since we have two different sets of stores) to test the
hypothesis. The SPSS output is given below -
Group Statistics
Std. Std. Error
Region N Mean Deviation Mean
Average Monthly Sales in West Coast 10 313.7570 15.97821 5.05275
Thousands of dollars East Coast 10 328.8360 21.06402 6.66103
Independent Samples Test
Levene's
Test for
Equality
of
Variances t-test for Equality of Means
95%
Confidence
Significan Interval of the
ce Difference
One Two Std.
- - Mean Error
Sig Side Side Differen Differen
F . t df dp dp ce ce Lower Upper
Average Equal 1.34 .26 - 18 .044 .088 - 8.36060 - 2.4859
Monthly varianc 1 2 1.80 15.07900 32.6439 6
Sales in es 4 6
Thousan assume
ds of d
dollars Equal - 16.78 .045 .089 - 8.36060 - 2.5778
varianc 1.80 1 15.07900 32.7358 7
es not 4 7
assume
d
One sided p value is 0.044.
Comparing the p value with alpha = 0.05, we find that the p value is less than the alpha.
Therefore, we reject the null hypothesis. That means, the sales for the stores in the east coast is
higher than sales in the west coast.
3. A home improvement store recently purchased a new paint color-mixing machine. The
machine is rated to produce 5 gallons of mixed paint every minute. The store’s manager
suspects that the machine is underperforming. In order to test his hypothesis, the manager
tests the machine’s output by mixing 10 randomly chosen colors and measuring the
output rate of the machine. The data is in colormix.sav (data set is provided in the D2L
content area in Module 3, Assessment section). State the hypothesis, conduct the
appropriate test using SPSS and interpret the results.
15 points
Answer:
The hypothesis can be stated as –
H0: >= 5
Ha: < 5
= 0.05
Where represents mean produce of mixed paint by the machine.
The hypothesis states that the machine is producing less than 5 gallon of mixed paint per minute
which is stated as the alternate hypothesis. The opposite is the null hypothesis.
In order to test this hypothesis, we run a one sample t-test in SPSS and compare the data with 5.
The SPSS output is provided below –
One-Sample Statistics
N Mean Std. Deviation Std. Error Mean
Gallons per minute 10 4.6600 .58157 .18391
One-Sample Test
Test Value = 5
95% Confidence
Interval of the
Significance Difference
One- Two- Mean
t df Sided p Sided p Difference Lower Upper
Gallons per -1.849 9 .049 .098 -.34000 -.7560 .0760
minute
The one-sided p value is 0.049.
Comparing the one-sided p value with the alpha = 0.05, we see that the p value is less than alpha.
Hence, the null hypothesis is rejected. That means, the machine is underperforming.
4. The data in TECHPRO.sav, obtained from Business Week’s (June 22, 2006) technology
section, represents typical salaries of technology professionals in 13 metropolitan areas
for 2003 and 2005. Suppose you want to determine if the mean salary of technology
professionals at all US. Metropolitan areas have increased between 2003 and 2005.
(a) Set up the null and alternative hypothesis for the test. 5 points
(f) Conduct the appropriate test and provide your conclusion. More specifically, I want
you to examine whether the null hypothesis should be rejected by analyzing the data
with SPSS.
10
points
Answer:
The hypothesis can be stated as –
H0: 1 - 2 >= 0
Ha: 1 - 2 < 0
= 0.05
Where 1 is the mean salary in the year 2003 and,
2 is the mean salary in the year 2005.
The hypothesis states that the salary of technology professionals in the metropolitan areas have
increased between 2003 and 2005. If that is the case, the mean salary in the year 2003 should be
less than the mean salary in the year 2005. This is stated as the alternate hypothesis 1 - 2 < 0.
The opposite is stated as the null hypothesis.
In order to test this hypothesis, we run a paired sample t-test since same subject is measured
twice for the same variables. The SPSS output is provided below –
Paired Samples Statistics
Mean N Std. Deviation Std. Error Mean
Pair 1 SAL2003 72.869 13 5.8895 1.6334
SAL2005 74.846 13 5.9602 1.6531
Paired Samples Test
Paired Differences Significance
95% Confidence
Std. Interval of the One- Two-
Std. Error Difference Sided Sided
Mean Deviation Mean Lower Upper t df p p
Pair SAL2003 -1.9769 3.6030 .9993 -4.1542 .2004 -1.978 12 .036 .071
1 -
SAL2005
The one-sided p value is 0.036.
Comparing the one-sided p value with alpha = 0.05, we observe that the p value is less than
alpha. Therefore, the null hypothesis is rejected. Which means, the salary of technology
professionals in the metropolitan has increased between 2003 and 2005.
