MDCN2427

Research Methodology and Biostatistics

Dr. Amal Sahikhah PhD Medical Statistics,

2024-09-27 1
 Content
• Sampling designs
•Data collection
•Data analysis
 ILO

• 1-Define Basic Concepts related to Sampling from a

population.

• 2- Define inference from a Sample to a target population

• 3- Identify differences between random and non random

samples.

• 4- Understand advantages and disadvantages of each

sample type.

3
Basic Concepts in Sampling:

Target Population

• Target Population is defined according to the research objective .

• Guiding Qs:
• What is your population of interest?

• To whom do you want to generalize your results?

4
Examples of Target Population ……
• E.g.
• School children in Gaza
• Women aged 15-45 years
• All Hospital admissions within a
specified period
• Cancer Patients

5
SAMPLING BREAKDOWN
6
SAMPLING…….

STUDY POPULATION

SAMPLE

TARGET POPULATION

7
Basic Concepts in Sampling

• Sample: a subset of the population that should represent the

entire group

• Census: an accounting of the complete population

Ch 12 8
Technical Terminology

• Sample unit: the basic level of investigation (e.g.

Individual patient)
• The unit about which data is collected. .

• Sampling units are non overlapping

• Total units in the entire population-= Target population .
Technical Terms

• A sampling frame is a list of sampling units.

• A sample is a collection of sampling units drawn from a

sampling frame.

• Parameter: numerical characteristic of a population

• Statistic: numerical characteristic of a sample

Reasons for Taking a Sample

11
Reasons for Taking a Sample

• Practical considerations such as cost, time and effort.

• Samples can produce precise results

12
The purpose for sampling……

POPULATION

INFERENCE

SAMPLE
Statistical inference

• Statistical inference is the process of drawing conclusion about

population parameters based on statistics calculated from a
sample taken from
• the population.

Ch 12 14
Sampling error

• Sampling error or estimation error is the error caused by

observing a sample instead of the whole population. [1]

• The sampling error can be found by subtracting the value of a

parameter from the value of a statistic.

15
Types of Sampling Errors

1. Random Sampling error

2. Sampling bias
Factors Affecting size of random sampling
error:

❖ Sample design.

❖ Sample size.

❖ Level of confidence.
 Sampling bias…

…systematic error lead to invalid

findings

…sources of sampling bias include:

Use of volunteers,
available groups,
non responders,…..
What is a good sample?

Representative

Precise

Low Cost, Low Effort

Representative Sample

A representative sample mirrors

the characteristics of the
population and minimizes the
errors associated with sampling.
The Sampling Process

Define the Population

Determine the Sampling Frame

Select Sampling Technique(s)

Determine the Sample Size

Execute the Sampling Process

Sampling Methods

22
Two Basic Sampling Methods

• I-Non-probability samples: the probability of selecting

members from the population into the sample are unknown

• II-Probability samples: members of the population have a

known chance (probability) of being selected into the
sample

Ch 12 23
 Classification of Sampling Techniques

Sampling Techniques

Nonprobability Probability
Sampling Techniques Sampling Techniques

Convenience Judgmental Quota Snowball

Sampling Sampling Sampling Sampling

Simple Random Systematic Stratified Cluster Other Sampling

Sampling Techniques
Sampling Sampling Sampling
I-Non-probability samples

25
Nonprobability Sampling

• May not be representative but they are still used, Why?

• Decision makers want fast, relatively inexpensive answers…

26
Nonprobability Sampling

• The problem is that these samples may be biased because

not everyone gets a chance of selection.

27
Nonprobability Sampling

• Types:
• Convenience sampling
• Judgment sampling
• Referral sampling
• Quota sampling

28
I-Non-probability samples

Ch 12 29
CONVENIENCE SAMPLING

• the sample being drawn from that part of the population

which is close to hand. That is, readily available and
convenient. (Sometimes known as grab or opportunity
sampling or accidental or haphazard sampling.)

• This type of sampling is most useful for pilot testing.

•
30
Judgmental sampling or Purposive
sampling
• - The researcher chooses the sample based on who they
think (Judge) would be appropriate for the study.

• This is used primarily when there is a number of people that

have expertise in the area being researched

31
Snowball Sampling
Overview

▪ Study subjects recruit other subjects from people

they know
▪ Often used in hidden populations – commercial sex
workers, iv drug users,
▪ People who have many friends are more likely to be
recruited
▪ Friends tend to have similar characteristics
QUOTA SAMPLING

• The population is first segmented into mutually

exclusive sub-groups, just as in stratified sampling.

• Then non randomly select subjects or units from

each segment based on a specified proportion.
•
• For example, an interviewer may be told to sample
200 females and 300 males between the age of 45
and 60.
•.

33
Probability Sampling Methods

Ch 12 34
Probability Sampling Methods

• 1-Simple random sampling

• 2-Systematic sampling
• 3-Cluster sampling
• 4-Stratified sampling

35
1-SIMPLE RANDOM SAMPLING
• Applicable when population is small, homogeneous & readily
available→ has a sample frame

• A table of random number or computer program is used to

determine which units are to be selected.

• Each element of the frame thus has an equal probability of

selection.

36
SIMPLE RANDOM SAMPLING……..
• Estimates are easy to calculate.

• Disadvantages
• If the target population is v. large, this method
necessitating accurate sample frame is impractical.

• Minority subgroups of interest in population may not be

present in sample in sufficient numbers for study.

37
2- Systematic Sampling
• When to use:
• When the sample units are arranged in a systematic way.

Ch 12 38
SYSTEMATIC SAMPLING……

• ADVANTAGES:
• Sample easy to select
• Suitable sampling frame can be identified easily
• Sample evenly spread over entire reference population

• DISADVANTAGES:
• Sample may be biased if hidden periodicity in population
coincides with that of selection.

• Small loss in sampling precision

39
3-Stratified Sampling

Ch 12 40
3-Stratified Sampling

When To Use:
• When the answer to the research question are likely to vary by
subgroups (Strata) in the target population…

41
Stratified Random Sampling

Basic ideas:

• A stratified random sample is obtained by

separating population elements into non-
overlapping groups (strata) and selecting a
simple random sample from each stratum.
Advantages of stratification:

1. Higher in precision – this is possible by dividing a heterogeneous

population into strata in such a way that each stratum is internally
homogeneous.

2. Fieldwork is organized by strata, which usually result in saving in

cost.

3. To obtain separate estimates for strata.

Advantages of stratification:
• Stratified sampling allows the researcher to allocate more sample
size to strata with high variance and less sample size to strata with
less variance.

• Thus, for the same sample size, more precision is achieved.

44
Proportionate Stratified Sampling

Ensures that the ratio of important categories in the sample

remains similar to that in the population.

Population Sample

45
4- CLUSTER SAMPLING…….

46
 Cluster sampling:

Cluster= a group of similar things or people positioned or occurring closely together .

Cluster sampling is the process of randomly

selecting groups, not individuals,

Any of the selected group(cluster) can be

considered a representative sample for the
target population.
When Cluster sampling is preferred ?

• Cluster sampling is preferred when:

• (i) No reliable listing of all units of the target population is

available and it is expensive to prepare it.

• (ii) The location of all units may be difficult to reach.

Ch 12 48
Construction of clusters:

All clusters are similar and within each cluster the

sampling units are heterogeneous and similar to the
general population

• N.B.: This is opposite to the construction of the strata in

the stratified sampling.

Ch 12 49
 Differences Between Strata and
Clusters

❖1- stratified sample: All strata are represented in the sample.

Cluster sample: Only a subset of clusters are in the sample

❖2- Stratified sample: Best survey results occur when elements within
strata are internally homogeneous.

Cluster sampling: Best results occur when elements within clusters are
internally heterogeneous the same as the total population.

50
MULTI-STAGE SAMPLING

• Complex form of cluster sampling in which two or more

levels of units are embedded one in the other.

• First stage: Select random number of governorates

(clusters) chosen from the country.

• Second stage: random number of districs ( subcluster) in

each governorate.

• Third stage: units could be houses within each district

selected by systematic random sample.

• …….

51
Ch 12 52
MULTI PHASE SAMPLING

• Part of the information collected from whole sample & part

from subsample.

• In TB survey tuberculin test in all cases – Phase I

• X –Ray chest in tuberculin test +ve cases – Phase II

• Sputum examination in X – Ray +ve cases - Phase III

• Survey by such procedure is less costly, & more purposeful

53