Epi X Sampling

University Grants Commission-
National Eligibility Test (NET)

Epidemiology
Sampling & Sample Size
Estimation
Dr. Shamim Mohammad, M.Phil., PhD.

International Ford Foundation Alumnus
Email: Shamim_ifff@yahoo.co.in
What is a Sample &
Sampling Theory?
•Sample: A sample is “a smaller (but hopefully
representative) collection of units from a
population used to determine truths about that
population”
•Theory
• The sample must provide an accurate picture of the population from
which it is drawn
• The sample should be random; each individual in the population should
have an equal chance of being selected
What is Sampling?
•Often it is impractical to examine an entire population
•Instead, we select a sample from our population of interest and, on the
basis of this sample, information about the entire population will be
inferred
Why Sample?
Availability
Availability of
of Lower
Lower cost
cost
elements
elements
Sampling
Sampling
provides
provides
Greater
Greater Greater
speed
speed accuracy
Population Vs. Sample
Population of Interest
Population Sample
Sample
We measure the sample using statistics in Parameter Statistic

order to draw inferences about the
population and its parameters.
5
Statistical Inference
The
The purpose
purpose ofof statistical
statistical inference
inference is
is to
to obtain
obtain information
information about
about
Population
Population from
from information
information contained
contained in
in a
a sample.
sample.
A
A population
population is
is the
the set
set of
of all
all the
the elements
elements of
of interest
interest..
A
A sample
sample is
is a
a subset
subset of
of the
the population
population..
The
The sample
sample results
results provide
provide only
only estimates
estimates of
of the
the values
values of
of the
the pop
pop
characteristics.
characteristics.
With
With proper
proper sampling
sampling methods,
methods, the
the sample
sample results
results can
can provide
provide “g
“g
estimates
estimates of
of the
the population
population characteristics.
characteristics.
Sampling Frame and
Sampling Plan
•Sampling frame: A listing of every member of the population,
using the sampling criteria to define membership in the
population
•Subjects are selected from the sampling frame
•Sampling plan: Outlines strategies used to obtain a sample for
a study
◦ Probability sampling plans
◦ Nonprobability sampling plans
Types of Sampling Methods
Probability Samples
Non-Probability Samples
Simple Stratified
Random
Quota
Judgemental
Systematic Cluster
Convenience
8
Probability Sampling Method
In probability sampling
The random ("equal chance“) and "independent" components
of random sampling are what makes us confident that the
sample has a reasonable chance of representing the population
A sampling frame exists or can be compiled.
should have an equal or at least a known or nonzero chance
of being included in the sample.
Generalization is possible (from sample to population)
9
Types of Probability
Sampling
Simple random sampling
Stratified random sampling
Cluster sampling
Systematic sampling
Simple Random Sampling
USAID and WINROCK

Simple Random Sampling
•Method of lottery
•The researcher gives each
member of the population a
number. Researchers draw
numbers from the box randomly to
choose samples.
•Use of random numbers
•The use of random numbers
(Table) is an alternative method
that also involves numbering the
population.
https://www.questionpro.com/blog/simple-random-sampling/
Advantages of SRS
A fair method of sampling
It helps to reduce any bias involved compared to any
other sampling method.
Easy to pick a smaller sample size from the existing
larger population.
The researcher need not be a subject expert.
Only listening and recording skills required.
From a larger population, you can get a small sample
quite quickly.
More the samples better is the quality of the data.
Example of SRS
•n/N
•For example, in an organization of 500
employees, if the HR team decides on
conducting team building activities, it is
highly likely that they would prefer picking
chits out of a bowl. In this case, each of the
500 employees has an equal opportunity of
being selected.
•50/500=1/10x100=10%
Systematic Sampling
USAID and WINROCK

Example SS
•Views on contraception/abortion
•This method of
are to be selected from 1,200
choosing the nth students from the college. The
member is called required sample size is 100. The
systematic sampling. study population is 1,200 and
•Systematic sampling is the sample size is 100, so a
systematic sampling interval is
usually less time- found by dividing the study
consuming and easier to population by the sample size:
perform than simple
•1,200 ÷ 100 = 12
random sampling
https://www.open.edu/openlearncreate/mod/oucontent/view.php?id=233&section=1.5.2
Stratified Sampling & Its
Merits
A method of sampling that Stratification is most
involves the division of a useful when the
population into smaller sub- stratifying variables are
groups known as strata. Simple to work with,
Strata is homogeneous and Easy to observe,
mutually exclusive categories
(age, sex, residence, cate, Closely related to the
religion….etc.) topic of the survey.
Stratified Sampling
USAID and WINROCK

Cluster Sampling
USAID and WINROCK

Cluster Sampling
•Researchers divide the population into internally
heterogeneous and externally homogeneous subpopulations
known as clusters
•Clusters may be divided by different cities in a country,
different areas in a city, different organizations, different
universities, different industrial estates etc.
•Example, if you were to conduct a study on the consumption
of soda in a particular city, you could use area sampling to
divide the city into different areas, called clusters, and then
select certain clusters to be a part of the sample group.
Characteristics of Good Samples
3 factors that influence sample representativeness
◦ Sampling procedure
◦ Sample size
◦ Participation (response)
When might you sample the entire population?
◦ When your population is very small
◦ When you have extensive resources
◦ When you don’t expect a very high response
oAccessible
oLow cost 21
Errors in statistical Study
A sample is expected to mirror the population from which it comes,

however, there is no guarantee that any sample will be precisely
representative of the population.
No sample is the exact mirror image of the population .
Sampling or Random
Errors
Non-sampling or systematic
22
What is a sampling error?
•Difference between the population mean and the mean
of the sample
•Random variation is:
◦ The expected difference in values that occurs when
different subjects from the same sample are examined
◦ Difference is random because some values will
be higher and others lower than the average
population values
Non Sampling Error or bias
Error in the design or conduct of a sampling procedure which results in
distortion of the sample, so that it is no longer representative of the reference
population.
A non-response error occurs when units selected as part of the sampling
procedure do not respond in whole or in part (non response rate >15%)
A response or data error is any systematic bias that occurs during
data collection, analysis or interpretation
Respondent error (e.g., lying, forgetting, etc.)
Interviewer bias
Recording errors
Poorly designed questionnaires
24
What is attrition and retention
in reference to research
samples?
•Sample attrition is the withdrawal or loss of
subjects from a study
◦Attrition rate = number of subjects withdrawing
÷ number of study subjects × 100
•Sample retention is the number of subjects who
remain in and complete a study
Study population (N = 20,000) consisting
Random Samples
of five subgroups based on their
preferred lunch times. Preferred lunch
times, each a 30-minute interval,
Four samples of 10 subjects. Each mean
is a point estimate, the best predictor of
the unknown population mean.
None of the samples shown is a perfect
duplication because no sample perfectly
replicates its population.
We cannot judge which estimate is the
true mean of the population but we can
estimate the interval in which the true
mean will fall by using any of the
samples.
Standard Error of the Mean
/Standard Error
•The SD describes variability in a data set whereas SE refers to the
variability in the means of repeated samples from the same
population.
•The SE quantifies the variations in the sampled means (SD/)
•Assumption
•Infinite numbers of possible samples can be drawn from the source
population
•Utility
•Helps in calculating confidence intervals
Confidence Intervals
•Assumption: Central Limits Theorem- Attribute of the
obtained samples are equal to true value of the
population.
•Values obtained by the sample are distributed normally
about the true value, some will get higher and some lower
values
•In a normal distribution approximately, 95% of the means
would be expected to fall within the range of two standard
errors above and two below the mean of these means.

Epi X Sampling

Uploaded by

Copyright:

Available Formats

Epi X Sampling

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Epi X Sampling

Uploaded by

Copyright:

Available Formats

University Grants Commission-

National Eligibility Test (NET)

Dr. Shamim Mohammad, M.Phil., PhD.

We measure the sample using statistics in Parameter Statistic

Stratified random sampling

USAID and WINROCK

USAID and WINROCK

USAID and WINROCK

USAID and WINROCK

A sample is expected to mirror the population from which it comes,

You might also like