Download as docx, pdf, or txt
Download as docx, pdf, or txt
You are on page 1of 6

Estimating Sample Size

The sample size of any empirical research is important in making inferences about a particular
population from a sample. Sample size estimation is the act of choosing the sample or the
number of observations to include in the statistical sample.

*The term “sample” refers to the portion of the population that enables us to draw
inferences about the population. So, the sample size must be adequate to make
meaningful inferences. In other words, it is the minimum size needed to estimate the
true population proportion with the required margin of error and confidence level.

*Sample size calculation is important to understand the concept of the appropriate


sample size because one may use it to validate research findings. In case it is too small, it
will not yield valid results, while a sample that is too large may be a waste of both money
and time. Therefore, one should use a considerable sample size for market research,
healthcare, and education surveys.

There are some factors to consider when deciding on the sample size such as cost, time, and
convenience of collecting data, and the need for it to offer sufficient statistical power or
reliability.

Sample sizes may be chosen in several ways:

(a) using experience,

(b) using a target variance for an estimate to be derived from the sample eventually obtained,

(c) using a target for the power of a statistical test to be applied once the sample is collected,
and

(d) using a confidence level, wherein larger confidence levels would require a larger sample
size.

Determining Key Values


Step 1: Identify the population size. The population size pertains to the total number of people
within one's demographic.

*Your sample size requirements will vary depending on the true population size or total
number of people you want to draw conclusions from. That’s why determining the minimum
number of individuals required to represent your selection is an important first step.

Step 2: Determine the margin of error. The margin of error (also known as "confidence
interval") refers to the amount of error the researcher would allow in the results in the same
aforementioned tracer study, the researcher assigned a 5% margin of error.

*Random sample errors are inevitable whenever you’re using a subset of your total
population. Be confident that your results are accurate by designating how much error
you intend to permit.

Step 3: Set the confidence level. The confidence level is a value that measures the degree of
certainty regarding how well a particular sample represents the overall population within the
chosen margin of error. For the same study, a 95% confidence level was set.

*Your confidence level reveals how certain you can be that the true proportion of the
total population would pick an answer within a particular range. The most common
confidence levels are 90%, 95%, and 99%. Researchers most often employ a 95%
confidence level. Using zscores helps you find the correct value for your calculation.

*Confidence level corresponds to something called a "z-score." A z-score is a value that


indicates the placement of your raw score (meaning the percent of your confidence
level) in any number of standard deviations below or above the population mea

Step 4: Specify the standard deviation. The standard deviation indicates the extent of variation
expected among the responses. Extreme answers are more likely to be more accurate than
moderate results. For the same study, the standard deviation was 0.50.

*Standard deviation measures how much individual sample data points deviate from the
average population. Using the standard deviation of 0.5 help us to make sure that our group is
large enough.
Step 5: Find the Z-score. The Z-score is a constant value automatically set based on the
confidence level. It indicates the "Standard normal score" or the number of standard deviations
between any selected value and the average or mean of the population. These scores are fairly
standardized as follows:

80% confidence> 1.28 z-score

85% confidence => 1.44 z-score

90% confidence => 1.65 z-score

95% confidence => 1.96 z-score

99% confidence => 2.58 z-score

n.

The Standard Formula


The standard formula for estimating the sample size for an empirical study is illustrated as
follows:

[Z² x p (1-p)]/e²

n=
1+[{Z x p (1-p)}/e²N]

For example, a university is embarking on a study evaluating the entrepreneurial interests of its
alumni (ie, graduates in the past 10 years). Records reveal that the school produced 5,487
graduates in the said period.

where:

N = population size 5,487 graduates

Z = Z-score 1.96

e=margin of error 5% or 0.05

p=standard deviation 0.5

Upon substitution of the known amounts in the abovementioned standard formula, the value
of n is calculated as follows:

1.96² x [0.5 (1-0.5)]/0.05²

n=

1+[{1.96² x 0.5 (1-0.5)}/(0.05² x 5,487)]

n=359.02 or 360 (Always round off to the next digit.)

Thus, the sample size should be a minimum of 360 graduate-respondents for the said study.

Formula for Unknown or Very Large Populations


Step 1: Examine the formula. If one has a very large population or an unknown one,

use a secondary formula. For example, the province of Bulacan is conducting a study on the
level of tax compliance of its individual taxpayers (estimated at 1.2 million). With a confidence
level of 95%, standard deviation of 0.5, and a margin of error of 3%, calculate the value of n.
n = [Z² x p(1 - p)] / e²

where substituted

Z = Z-score 1.65

e = margin of error 3% or 0.03

p = standard deviation 0.5

Step 2: Substitute the values in the equation. Replace each variable with the numerical values
identified.

n = [1.65² x 0.5 [1 - 0.5)] / 0.03²

n = 1,067.11 or 1,068 taxpayer-respondents

Slovin's Formula

Step 1: Understand the standard formula. Slavin's formula is a general equation used when one
can estimate the population but does not have an idea about how a certain population
behaves; hence, it has become a popular method of sample size estimation.

n = N / (1 + Ne²)
For example, an auditor wanted to estimate the sample size needed to satisfy the requirement
for a research undertaking confirming the balances of depositors of a commercial bank. There
are 168,540 depositors of the bank. The error of margin is 5%.

Step 2: Substitute the values. Plug in the numbers to be able to calculate the value of n.

n = 168, 540 / [1 + [168, 540 x 0.05²)]

n = 399.05 or 400 depositor respondents

You might also like