2. One tailed test of means
• A hospital uses large quantities of packaged doses of a
particular drug. The individual dose of this drug is
100cc. The action of this drug is such that the body will
harmlessly pass off excessive doses. On the other hand
insufficient doses do not produce the desired result.
The hospital has purchased this drug from the same
manufacturer for the last 2 yrs and knows that the
population s.d. is 2 cc. The hospital inspects 50 doses
of this drug from a very large shipment and finds the
mean of these doses to be 99.75 cc. If the hospital sets
a 0.10 significance level, should the shipment be
accepted?
3. • Hinton press hypothesizes that the average
life of its largest web press is 14500 hrs. They
know that the s.d. of press life is 2100 hrs.
From a sample of 25 presses, they find a
sample mean of 13000 hrs. At a .01
significance level, should the company
conclude that the average life of the presses is
less than 14500 hrs?
4. Two tailed tests of proportions-large
samples
• A company is evaluating the proportion of the
employees who are promotable to the next level.
The HR director tells the president that approx.
80% of the employees in the company are
promotable. An evaluation committee does an
in-depth interview of 150 employees and
concludes only 70% of the employees in the
sample are promotable. The president wants to
test at a significance level of 0.05 the hypothesis
that 0.8 of the employees are promotable.
5. • A personnel specialist is recruiting a large
number of specialists for an overseas
assignment. During the testing process, when
asked how things were progressing, she said “
I think the average score will be around 90”.
When management reviews 20 of the tests
compiled, it finds that the mean score is 84
with a s.d. of 11. If management wants to test
her hypothesis at 0.10 level of significance
what should it do?
6. Hypothesis testing-differences
between means and proportions
• Sampling distribution of difference between
means
• Mean of Sampling distribution of difference
between means
• Standard error of difference between 2 means
7. • A manpower development statistician is asked
to determine whether the hourly wages of
workers are the same in 2 cities. The data are
in the attached table. The company wants to
test at 0.05 level whether there is no
difference between the wages for workers in
the two cities.
8. Hourly S.D . Of sample Size of sample
earnings from
sample
City 1 8.95 0.40 200
City 2 9.10 0.60 175
9. Differences between means-
dependant samples
• A health spa has advertised a weight reducing
program and claims that the average participant will
lose more than 17 pounds. A somewhat overweight
executive is interested in the program, but wants
some hard evidence. The spa allows him to select 10
participants at random and record their weights
before and after the program.The overweight exec
wants to test at 5% level of significance the claimed
average weight loss of more than 17 pounds.
10. Weight (lbs): Before and after
Befor 189 202 220 207 194 177 193 202 208 233
e
After 170 179 203 192 172 161 174 187 186 204
11. Tests for differences in
proportions: large sample sizes
• Standard error of the difference between
proportions
12. • A pharma company wants to test 2 new compounds
intended to reduce blood pressure levels. The
compounds are administered to two different sets of
laboratory animals. In group 1, 71 out of 100 animals
tested responded positively to drug-1. In group 2, 58
out of 90 animals tested responded positively to
drug 2. The company wants to test at .05 level
whether there is a difference between the efficacies
of the two drugs