BIOSTATISTICS

LECTURE 4
SAMPLING TECHNIQUES
AND
SAMPLE SIZE DETERMINATION
BY
DR. SAMIRA FAIZ
 Sample
A sample is a subset from human groupings

selected to represent the population

OR

A group of people chosen from the population on which

the research is conducted
 Sampling

Sampling is the process of selecting a small number of

elements from a larger defined target group of elements

such that the information gathered from the small group

will allow judgments to be made about the larger groups.

 Target Population

The target population is the total collection of elements or

objects that possess the information sought by the researcher

and about which inferences are to be made.

 Sampling Frame
• A list of population units and elements (people,

companies, houses, cities, etc.) from which the sample

can be drawn.
 Sample

A sampling unit contains the element. In some cases the

sampling unit can be the element itself.

An element is the object about which or from which the

information is desired: respondents, products, stores,

companies, families
 Probability

Probability means that each element has

the same or equal chance of being

included in the sample

 Sampling Methods

Probability Non-probability
sampling sampling
• Probability samples: ones in which members

of the population have a known chance

(probability) of being selected

• Non-probability samples: instances in which

the chances (probability) of selecting members

from the population are unknown

 Classification of Sampling Techniques
Sampling Techniques

Nonprobability Probability
Sampling Techniques Sampling Techniques

Convenience Purposive Quota Snowball

Sampling Sampling Sampling Sampling

Simple Random Systematic Stratified Cluster Multistage

Sampling Sampling Sampling Sampling Sampling
Probability Sampling Methods
 Simple Random Sampling
Simple random sampling: the probability of being selected is

“known and equal” for all members of the population

1. Blind Draw Method or Lottery Method (e.g., names “placed in

a box” and then required number drawn randomly)

2. Random Numbers Method (all items in the sampling frame

given numbers, numbers then drawn using table or computer

program)
 Systematic Sampling
• The sample is chosen by selecting a random starting point and then

picking every nth element in succession from the sampling frame.

• The sampling interval is determined by dividing the population size N by

the sample size n and rounding to the nearest integer.

• Sampling Interval = N / n nth number or kth

 Systematic Sampling Ctd…

For example, there are 100,000 elements in the

population and a sample of 1,000 is desired.

 In this case the sampling interval is 100

 A random number between 1 and 100 is selected. If,

for example, this number is 23 the NEXT

NUMBERS are 123, 223, 323, 423, 523, and so on.

 Stratified Sampling
• One of the main purpose of stratified sampling is to compare

different strata or groups

• The population is first divided into groups (strata) according to one

or more characteristics:

• Members of each strata share same characteristics

• Age, gender, economic status, religion etc

• Follow a simple random or systematic sampling procedures

 Cluster Sampling
• When a list of the entire area is not available and it is not

physically possible to visit the entire area(e.g. the city, or

country) one can divide the area into several equal size clusters

• One can select (randomly) only a few clusters

• Number all the units and draw either a random samples or a

systematic sample from the selected cluster.

Stratified Sampling Cluster Sampling
Groups ensure the sample reflects Groups reduce costs and allow
all relevant subgroups and can researchers to sample large
produce better group estimates. populations.
Each group is relatively
Each group reflects the full
homogeneous compared to
diversity of the population.
the whole population.
Groups should be different from Groups should be identical to
each other. (cannot be replaced each other. (can be replaced with
with each other) each other)
Reduced errors More errors
Non-Probability Sampling Methods
 Convenience Sampling
Convenience sampling or Accidental attempts to obtain a

sample of convenient elements. Often, respondents are selected

because they happen to be in the right place at the right time.

• Students in library

• Shopping mall intercept interviews without qualifying the

respondents

• “People on the street” interviews

Judgmental (Purposive) Sampling
Samples that require a judgment or an “educated guess” on the

part of the interviewer as to who should represent the

population. Sampling done on the basis of some pre-

determined idea (clinical knowledge) .

Subjectivity enters in here, and certain members of the

population will have a smaller or no chance of selection

compared to others
 Quota Sampling
In Quota sampling the strata of population are identified
and the researchers determine the proportions of elements
needed from various segments. The quota of sample for
various groups is decided by the researchers for a pre-
determined purpose.
 Stratified sampling relies on the
random selection within each group
while,
Quota sampling relies on convenience
sampling within each group.
 Snow-Ball Sampling
In snowball sampling, an initial group of respondents is
selected, usually at random.
• After being interviewed, these respondents are asked to
identify others who belong to the target population of
interest.
• Subsequent respondents are selected based on the
referrals.
• Examples: injecting drug users, eunichs, transgenders,
HIV/AIDS positive
 Advantages & Disadvantages of Sampling Methods

Probability Non-Probability
Advantages Advantages

 Minimal sampling bias  Convenient

 Sampling error can be estimated  Economical

 More authentic  Less skillful

Disadvantages Disadvantages

 Expensive  Results can not be generalized

 Inconvenient  Maximum bias

 Time consuming  Authenticity very debatable

 Sampling Error
Sampling error is any type of bias that is attributable to mistakes in either
drawing a sample or determining the sample size

A sampling error is a statistical error that occurs when an analyst does not
select a sample that represents the entire population of data.

As a result, the results found in the sample do not represent the results that
would be obtained from the entire population.
 Types of Sampling Errors
There are different categories of sampling errors.
• Population-Specific Error occurs when a researcher doesn't understand
who to survey.
• Selection Error occurs when the survey is self-selected, or when only those
participants who are interested in the survey respond to the questions.
Researchers can attempt to overcome selection error by finding ways to
encourage participation.
• A sample frame error occurs when a sample is selected from the
wrong population data.
• A non-response error occurs when a useful response is not obtained from
the surveys because researchers were unable to contact potential
respondents (or potential respondents refused to respond).
 Eliminating Sampling Errors
• Sampling errors can be reduced by increasing the sample size. As the
sample size increases, the sample gets closer to the actual population, which
decreases the potential for deviations from the actual population.
• Researchers might attempt to reduce sampling errors by replicating their
study. This could be accomplished by taking the same measurements
repeatedly, using more than one subject or multiple groups, or by
undertaking multiple studies.
• Random sampling is an additional way to minimize the occurrence of
sampling errors by establishing a systematic approach to selecting a sample.
For example, rather than choosing participants to be interviewed
haphazardly, a researcher might choose those whose names appear first,
10th, 20th, 30th, 40th, and so on, on the list.
 IMPORTANT
A sampling error can result even when no mistakes of
any kind are made; sampling errors occur because no
sample will ever perfectly match the data in the
universe from which the sample is taken.
 Sampling Errors
The factors that influence the sampling error are:

i. The size of the sample (sample size ; sampling error )

ii. The natural variability of the individual readings (the individual

readings vary widely; we get more sampling errors)
 Non-Sampling Error
Non-sampling errors are errors that result during data collection and

cause the data to differ from the true values. Non-sampling errors are

caused by human error, such as a mistakes made in the survey

process.
For example:
• observation errors
• defective instruments
• incomplete coverage of the selected subjects
SAMPLE SIZE
DETERMINATION
SAMPLE SIZE DETERMINATION
SAMPLE SIZE ESTIMATION - STUDY DESIGN
SAMPLE SIZE ESTIMATION – PRIMARY
OUTCOME MEASURE
SAMPLE SIZE CALCULATION
• It is now understood that sample Size is calculated differently for different study
scenarios and there could be a lot of such scenarios but mostly the following two
situations are encountered:

1. Calculating Sample Size for a One Sample Proportion

2. Calculating Sample Size for comparison of two proportions

SAMPLE SIZE CALCULATION FOR A SINGLE
PROPORTION
▪ Three factor are key to calculate the sample size for a single proportion:

1. Confidence Level

2. Standard Error/Effect Size OR standard Deviation of Mean

3 . % frequency of the outcome factor i.e., PREVALENCE

EXAMPLE
▪ An investigator is interested in estimating the prevalence of respiratory
illness among carpenters, using 95% confidence interval and the error of 5%.
Previous studies suggest that the prevalence of is 20%. Calculate the sample
size.
SAMPLE SIZE CALCULATION FOR TWO
PROPORTIONS
▪ Three factor are key to calculate the sample size for comparison of two
proportions:

1. Confidence Level

2. Standard Error/Effect Size

3. Power of study
FORMULA
EXAMPLE
▪ A researcher is interested in comparing the average birth weight of children
born to smoking and non-smoking women, using 9 5 % confidence interval
and a power of study (1 – β) is taken as 80% and previous studies suggest that
the prevalence of first proportion is 50% whereas that of second proportion is
25%. Calculate the sample size
Thank you