SAMPLE SIZE

By Dr E. A. Kassembe
Snr Lect
Dar es Salaam Maritime Institute
The Sample Size
• The sample size is a term used in market research for defining the
number of subjects included in a sample size. By sample size, we
understand a group of subjects that are selected from the general
population and is considered a representative of the real population for
that specific study.

• For example, if we want to predict how the population in a specific age

group will react to a new product, we can first test it on a sample size
that is representative of the targeted population. The sample size, in
this case, will be given by the number of people in that age group that
will be surveyed.
The Sample Size
The Sample Size
• We cannot test the entire population.
• The sample size is based on confidence intervals: we are interested in
calculating the population parameter, in measuring the sample size.
• Therefore, we should establish the confidence intervals, so that of the values
of this sample lie inside that range.
• Sampling answers the question of how? How many? By population, we
understand all the members of a specific community and whose character is a
certain natural law, a specific characteristic, particularity .
• What is a good sample size? The sample size is a subset, an extract, several
persons extracted from that population. The population is considered infinite;
in practice, we cannot study an endless number of cases.
What is a “Sample Size”?
• A sample size is a part of the population chosen for a survey or
experiment. For example, you might take a survey of dog owner’s
brand preferences. You won’t want to survey all the millions of dog
owners in the country (either because it’s too expensive or time
consuming), so you take a sample size. That may be several thousand
owners.
• The sample size is a representation of all dog owner’s brand
preferences.
• If you choose your sample wisely, it will be a good representation.
When Error can Creep in
• When you only survey a small sample of the population, uncertainty
creeps in to your statistics.
• If you can only survey a certain percentage of the true population, you
can never be 100% sure that your statistics are a complete and
accurate representation of the population.
• This uncertainty is called sampling error and is usually measured by a
confidence interval. For example, you might state that your results are
at a 90% confidence level. That means if you were to repeat your
survey over and over, 90% of the time your would get the same
results.
The Cochran formula
• The Cochran formula allows you to calculate an ideal sample size given
a desired level of precision, desired confidence level, and the estimated
proportion of the attribute present in the population.

• Cochran’s formula is considered especially appropriate in situations

with large populations. A sample of any given size provides more
information about a smaller population than a larger one, so there’s a
‘correction’ through which the number given by Cochran’s formula can
be reduced if the whole population is relatively small.
The Cochran formula
• The Cochran formula is:

• Where:
1. e is the desired level of precision (i.e. the margin of error),
2. p is the (estimated) proportion of the population which has the attribute in
question,
3. q is 1 – p.
4. The z-value is found in a Z table.
What is a Z Table (Z Score Table)?
What is a Z Table (Z Score Table)?
What is a Z Table (Z Score Table)?
• Here is an example of how a z-score applies to a real life situation and
how it can be calculated using a z-table. Imagine a group of 200
applicants who took a math test. George was among the test takers and
he got 700 points (X) out of 1000. The average score was 600 (µ) and
the standard deviation was 150 (σ). Now we would like to know how
well George performed compared to his peers.

• We need to standardize his score (i.e. calculate a z-score corresponding

to his actual test score) and use a z-table to determine how well he did
on the test relative to his peers. In order to derive the z-score we need
to use the following formula:
What is a Z Table (Z Score Table)?
Finding a corresponding probability is fairly
• easy. Find the first two digits on the y axis (0.6
in our example).
•
Therefore: Then go to the x axis to find the second decimal
number (0.07 in this case). The number is
Z score = (700-600) / 150 0.7486. Multiply this number by 100 to get
= 0.67 percentages.
Now, in order to figure out how well George did on
So 0.7486 x 100 = 74.86%. This means that
the test we need to determine the percentage of his
almost 75% of the students scored lower than
peers who go higher and lower scores. That’s where z-
George and only 25% scored higher. 75% out of
table (i.e. standard normal distribution table) comes
200 students is 150.
handy. If you noticed there are two z-tables with
negative and positive values. If a z-score calculation
George did better than 150 students.
yields a negative standardized score refer to the 1st
table, when positive used the 2nd table. For George’s
example we need to use the 2nd table as his test
result corresponds to a positive z-score of 0.67.
Cochran’s Formula Example
• Suppose we are doing a study on the inhabitants of a large town, and want to
find out how many households serve breakfast in the mornings. We don’t
have much information on the subject to begin with, so we’re going to assume
that half of the families serve breakfast: this gives us maximum variability.
• So p = 0.5. Now let’s say we want 95% confidence, and at least 5 percent—
plus or minus—precision. A 95 % confidence level gives us Z values of 1.96,
per the normal tables, so we get

n0 =
n0 = 385
• So a random sample of 385 households in our target population should be
enough to give us the confidence levels we need.
Modification for the Cochran Formula for
Sample Size Calculation In Smaller Populations
• If the population we’re studying is small, we can modify the sample
size we calculated in the above formula by using this equation:

• Here n0 is Cochran’s sample size recommendation, N is the population

size, and n is the new, adjusted sample size. In our earlier example, if
there were just 1000 households in the target population, we would
calculate

• So for this smaller population, all we need are 278 households in our
sample; a substantially smaller sample size.
Yamane’s Formula for Sample Size
• Yamane’s formula is a simple formula to find sample size for proportions. Imagine that
you want to evaluate a program where 2000 teachers were encouraged to adopt a new
practice . Find the needed sample size at a 95% confidencelevel with ±5 % precision.
• Here is Yamane’s formula:

• Where:
• n = sample size
• e = precision level
• N = population size.
Yamane’s Formula for Sample Size
• n=
• n = 333.
• The table created with Yamane’s formula assumes 95% confidence
leve P = .5% (Maximum Variability)