Question: 21:

A chemical has mean specific gravity of 0.89 and standard deviation of 0.04. It is felt that the specific gravity increases
during summers by at least 0.01 whereas the standard deviation remains the same. Find the minimum sample size needed
to test the theory with power of test of 90%.

Results
Sample Target
Difference Size Power Actual Power
0.01 139 0.9 0.901145

Conclusion: A minimum sample size of 139 samples is required to test the theory.

Question: 22:

A browser is being tested for download speed. It has average speed of 1 sec per MB and standard deviation of 1.5. It is
felt that download speed increases during night by 0.5 sec. Find the minimum sample needed to test the theory with
power of the test as 90%.
Results
Sample Target
Difference Size Power Actual Power
0.5 97 0.9 0.901470
Conclusion: A minimum sample size of 97 samples is required to test the theory.

Question: 23:

A hospital wants to determine whether there is any difference in the average Turnaround time of reports of the
laboratories on their preferred list. They collected a random sample and recorded Turnaround time for reports of 4
laboratories. TAT is defined as sample collected to report dispatch. Analyze the data and determine whether there is any
difference in average turnaround time among the different laboratories at 5% significance level.

One-way ANOVA: Laboratory 1, Laboratory 2, Laboratory ... oratory 4

Method
Null hypothesis All means are equal
Alternative hypothesis Not all means are equal
Significance level α = 0.05
Equal variances were assumed for the analysis.

Factor Information
Factor Levels Values
Factor 4 Laboratory 1, Laboratory 2, Laboratory 3, Laboratory 4

Analysis of Variance
Source DF Adj SS Adj MS F-Value P-Value
Factor 3 79979 26659.7 118.70 0.000
Error 476 106905 224.6
Total 479 186884

Model Summary
S R-sq R-sq(adj) R-sq(pred)
14.9863 42.80% 42.44% 41.83%
Means
Factor N Mean StDev 95% CI
Laboratory 1 120 178.36 13.17 (175.67, 181.05)
Laboratory 2 120 178.90 14.96 (176.21, 181.59)
Laboratory 3 120 199.91 16.54 (197.23, 202.60)
Laboratory 4 120 163.68 15.09 (160.99, 166.37)
Pooled StDev = 14.9863

Conclusion: It is not possible to state whether there is any significant difference in average turnaround time among the
different laboratories.

Question: 24:

File EXH_STAT contains home prices of 29 homes that were sold recently (Data is in column: Price Index). The
historical median home price in the area was 115. Find out if there is sufficient evidence to prove that the median home
prices have increased.

Question: 25:

File EXH_STAT has values for midget (Data is in Column: Values). Test if there is reason to believe that population
mean is not equal to 5. Obtain the 90% confidence interval for the mean. Worksheet: EXH_STAT

Question: 26:

Effect of fuel additive on vehicles is being studied. Out of a total of 20 vehicles, 10 vehicles are chosen randomly and
mileage is recorded. In rest of the 10 vehicles, additive to be tested is added with the fuel and their mileage is recorded.
Find if the mileage increases by adding the fuel additive. Assume the same data was recorded if only 10 vehicles were
chosen and mileage was recorded before and after adding the additive. What method will you choose to find the result.
Worksheet: Paired T.mtw

Paired T-Test and CI: Without additive, With Additive

Descriptive Statistics
Sample N Mean StDev SE Mean
Without additive 10 16.35 2.73 0.86
With Additive 10 17.80 3.36 1.06

Estimation for Paired Difference

95% CI for
Mean StDev SE Mean μ_difference
-1.450 2.061 0.652 (-2.924, 0.024)
µ_difference: mean of (Without additive - With Additive)

Test
Null hypothesis H₀: μ_difference = 0
Alternative hypothesis H₁: μ_difference ≠ 0
T-Value P-Value
-2.22 0.053

Descriptive Statistics: With Additive, Without additive

Statistics
Variable Mean SE Mean StDev
With Additive 17.80 1.06 3.36
Without additive 16.350 0.863 2.729

Histogram (with Normal Curve) of With Additive

 Histogram (with Normal Curve) of With Additive
Mean 17.8
4
StDev 3.360
N 10

Frequency

0
10 12 14 16 18 20 22 24
With Additive

Histogram (with Normal Curve) of Without additive

Histogram (with Normal Curve) of Without additive

Mean 16.35
2.0
StDev 2.729
N 10

1.5
Frequency

1.0

0.5

0.0
10 12 14 16 18 20 22
Without additive

Paired T-Test and CI: Without additive, With Additive

Descriptive Statistics
Sample N Mean StDev SE Mean
Without additive 10 16.35 2.73 0.86
With Additive 10 17.80 3.36 1.06

Estimation for Paired Difference

95% Lower Bound
Mean StDev SE Mean for μ_difference
-1.450 2.061 0.652 -2.645
µ_difference: mean of (Without additive - With Additive)
Test
Null hypothesis H₀: μ_difference = 2
Alternative hypothesis H₁: μ_difference > 2
T-Value P-Value
-5.29 1.000

Conclusion: There is not sufficient Data to substantiate the assumption that there is an Increase in the Mileage after
the Addition of the Fuel Additive.

Question: 27:

Data of cost of tickets sold in thousands in a show for a month are tabulated for five different competent Circus groups.
Check if their means are different. Worksheet: 1-Way ANOVA.mtw

One-way ANOVA: Gem, Joyride, Starlite, Fantasy, Fun

Method
Null hypothesis All means are equal
Alternative hypothesis Not all means are equal
Significance level α = 0.05
Equal variances were assumed for the analysis.

Factor Information
Factor Levels Values
Factor 5 Gem, Joyride, Starlite, Fantasy, Fun

Analysis of Variance
Source DF Adj SS Adj MS F-Value P-Value
Factor 4 2715 678.7 6.14 0.000
Error 52 5751 110.6
Total 56 8466

Model Summary
S R-sq R-sq(adj) R-sq(pred)
10.5167 32.07% 26.84% 18.36%

Means
Factor N Mean StDev 95% CI
Gem 12 44.333 3.398 (38.241, 50.425)
Joyride 10 39.99 11.28 (33.32, 46.66)
Starlite 12 29.67 14.98 (23.57, 35.76)
Fantasy 11 43.52 8.92 (37.16, 49.88)
Fun 12 50.02 10.51 (43.92, 56.11)
Pooled StDev = 10.5167

Interval Plot of Gem, Joyride, ...

 Interval Plot of Gem, Joyride, ...
95% CI for the Mean
60

50
Data

40

30

20
Gem Joyride Starlite Fantasy Fun

The pooled standard deviation is used to calculate the intervals.

Conclusion: There is not sufficient Data to substantiate the assumption that there is an Increase in the Mileage after
the Addition of the Fuel Additive.

Question: 28.

The number of road accidents in a month are recorded for 12 months. Find if the average number of road accidents are
the same across all cities. Worksheet: Test for Equal Variances.mtw

Test for Equal Variances: Atlanta, Bismarck, New York, ... iego, Phoenix
Method
Null hypothesis All variances are equal
Alternative hypothesis At least one variance is different
Significance level α = 0.05
Bartlett’s method is used. This method is accurate for normal data only.

95% Bonferroni Confidence Intervals for Standard Deviations

Sample N StDev CI
Atlanta 12 13.7981 (8.8470, 28.3634)
Bismarck 12 22.4641 (14.4035, 46.1775)
New York 12 16.7241 (10.7232, 34.3783)
San Diego 12 5.1079 (3.2751, 10.4999)
Phoenix 12 15.7596 (10.1047, 32.3955)
Individual confidence level = 99%

Tests
Test
Method Statistic P-Value
Bartlett 18.27 0.001

Test for Equal Variances: Atlanta, Bismarck, New York, San Diego,...
 Test for Equal Variances: Atlanta, Bismarck, New York, San Diego,...
Bartlett’s Test
Atlanta P-Value 0.001

Bismarck

New York

San Diego

Phoenix

0 10 20 30 40 50
95% Bonferroni Confidence Intervals for StDevs

Conclusion: based on the sample size available and the p-value of 0.001, it can be concluded that there is significant
difference in the average number of road accidents per month in the 12 month period and at least one of the cities has a
different average number of road accidents per month during a 12 month period, with San Diego having the least
Bismarck having the most variation while Atlanta, New York and Phoenix having a similar average number of road
accidents per month in the 12 month period.

Question: 29.

A poll is carried out to find the acceptability of new Cricket coach by the people. It was decided that if the support rate
for the coach for the entire population was truly less than 25%, the coach would be fired. 2000 people participated and
482 people supported the new coach. Conduct a test to check if the new coach should be fired with 95% level of
confidence.

Test and CI for One Proportion

Method
p: event proportion
Exact method is used for this analysis.

Descriptive Statistics
95% Upper Bound
N Event Sample p for p
2000 482 0.241000 0.257257

Test
Null hypothesis H₀: p = 0.25
Alternative hypothesis H₁: p < 0.25
P-Value
 0.183

Power and Sample Size

Test for One Proportion
Testing p = 0.25 (versus < 0.25)
α = 0.05

Results
Sample Target
Comparison p Size Power Actual Power
0.241 19611 0.9 0.900002

Power Curve for One Proportion

Conclusion: Based on the analysis above, the minimum sample size required to make a conclusive decision to fire the
new coach would be about 19611. However, with only a sample size of 2000 respondents, the result is inconclusive to
make a decision to retain or fire the new coach.

Question: 30.

In response to serious pricing pressures, a large third-party administrator of health care plans has re-engineered its
customer service operation in order to reduce cost. The company is concerned that quality of service must not be
adversely impacted by the change. The company tracks customer perceptions of service levels using ongoing surveys.
Over the last year, the percent of customers who were completely or very satisfied averaged 90%. After running a pilot
of the proposed change, data was collected from 250 customers in a random sample. A total of 29 customers responded
that they were less than very satisfied. Even though the new process represents a 17% reduction in operating costs, the
company is hesitant to launch a new process that may have a negative impact on customer satisfaction. With 29
customers less than very satisfied, should the revised process be launched? (Use a significance level of 5%)