Confidence Interval: Difference between Two Population Means µ1 - µ2

standard error of difference between population means

NB: use sample variances (s 2 ) if population variances are unknown.

Example
1. A manufacturing company operates two factories A and B at two different
locations. The company wishes to establish the difference between the
average daily production levels (in metric tonnes) of the two factories. The
following data was obtained for this purpose:

Factory ni
A 2600 182 38
B 1980 150 32

Estimate at:
a) 90% confidence level
b) 95% confidence level
c) 99% confidence level.

Confidence Interval: Difference between Two Population Proportions π1 - π2

π1 - π2 = ( p1 – p2) ±

standard error of difference between two population

proportions

Examples
1. In 1998, a survey of 1654 Kenyans found that 37% believed that the “energy
crisis” was a hoax. In 2004, of 1814 Kenyans, 42% believed that the energy
crisis was a hoax. In order to determine the real size of the change, estimate
with 90% confidence the difference between the 1998 and 2004 proportions.
2. In a public opinion survey, 60 out of a sample of 100 high-income voters and
40 out of a sample of 75 low-income voters supported a decrease in sales tax.
Estimate the differences in population proportions, with 99% confidence.

3. In a random sample of 500 television sets from a large production line, there
were 80 defective sets. In a random sample of 200 television sets from a second
production line, there were 10 defective sets. Estimate with 95% confidence the
difference between the population proportions.

Selecting the Sample Size to Estimate Population Mean

One of the most common questions asked of statisticians is, how large should a
sample size be? The answer to this question depends on three factors:-
1. the parameter to be estimated
2. the desired confidence level of the interval estimator
3. the maximum error of estimation (or margin of error) , where error of
estimation is the absolute difference between the point estimator and the
parameter e.g the point estimator of µ is so that the error of estimation
is | - µ|
The maximum error of estimation is error bound and is denoted E.

Suppose the parameter of interest in an experiment is the population mean µ. The

confidence level estimator (assuming a normal population, with the population
variance known is:

If we want to estimate µ to with a certain specified bound B, we will want the

confidence interval estimator to be:

E=
Solving for n we get:

n = z2 σ2 used to determine the appropriate sample size for an

E2 interval estimate of the population mean at the
chosen/ desired confidence level.
A popular method for approximating σ is to begin by approximating the range of
the random variable. A conservative estimate of σ is the range divided by 4. i.e.

σ = Range
4
This produces a larger value of σ, which results in a larger value of n, which than
estimates µ with an interval at least as good as specified.

Examples
1. A previous study that investigated the cost of renting cars in Ireland found a
mean cost of approximately 80 Euros. per day and standard deviation 9.65
Euros for renting a family saloon car. In a new study that the organization
wishes to conduct, the project director specifies that a population mean daily
rental cost be estimated with a margin of error of 2 Euros and 95%
confidence level. Determine the appropriate sample size for this new study.
(Ans: n= 90 family saloon cars)
2. How large a sample should be selected to provide a 95% confidence interval
with a margin of error 10. Assume that the population standard deviation is
40.
3. A production manager would like to estimate the mean time required for
workers to complete a task on an assembly line. Assume she knows that σ is
80 seconds. How large a sample should she draw to estimate µ to within 5
seconds with;
i) 90 % confidence
ii) 95% confidence
iii) 99% confidence
4. Find n, given that we want to estimate µ within 10 units with 95%
confidence, assuming σ =100.
5. The operations manager of a large production plant would like to estimate
the average amount of time a worker takes to assemble a new electronic
component. After observing a number of workers assembling similar
devices, she noted that the shortest time taken was 10 minutes and the
longest time taken was 22 minutes. How large a sample of workers should
she take if she wants to estimate the mean number of assembly time within
20 seconds? Assume confidence level is to be 99%.
6. Determine the sample size necessary to estimate µ to within 10 units with
99% confidence. We know the range of the population is 200 units.
Selecting the Sample Size to Estimate Population Proportion
Recall:
π = p±z

Margin of error z
E=

Making n the subject of the formula, we obtain:

2

n = z pq
2

Examples
1. A firm wishes to estimate with a maximum allowable error of 0.05 and at
95% confidence level, the proportion of consumers who prefer its product.
How large a sample will be required in order to make such an estimate if the
preliminary reports indicate that 25% of all consumers prefer the firm’s
product? (n= 288)
2. In a survey, the planning value for the population proportion is p* = 0.35.
How large a sample should be taken to provide a 95% confidence interval
with a margin of error of 0.05?
3. The manager of bank feels that 35% of branches will have enhanced yearly
collection of deposits after introducing a hike in interest rate. Determine the
sample size such the mean proportion is within plus or minus 0.06 at a
confidence level of:
i) 90%
ii) 95%
iii) 99%
4. The director of a management school feels that 55% of students will have
enhanced performance if additional input is given to them. determine the
sample size such that the mean proportion is within plus or minus 0.10 at a
confidence level of 95%.