Sampling and data collection Flashcards
Definition of (target)population
the entire group of
elements or subjects which the researcher
wish to generalize study findings
* e.g. (i) COPD patients; (ii) Full time secondary
school students
definition of Accessible Population
– a subset or the
whole of the population to which the
researcher has reasonable access
* (i) COPD patients in receiving treatment in
public hospitals ; (ii) Full time secondary school
students in government schools
definition of elements
an object or subject on which a
measurement is taken. e.g. (i) a COPD patient; (ii) a full time
secondary school student
definition of sampling unit
non-overlapping
collections of elements from the population
that cover the entire population(i) a COPD patient or all COPD patients in
ward; (ii) a full time secondary school student
or a class of secondary school
definition of Sampling frame
– a list of sampling units
* e.g. (i) a list of all COPD patients in hospital; (ii)
a list of all full time secondary school students
definition of Sample
a collection of sampling units
“drawn” from a sampling frame or frames
definition of Strata
mutually exclusive segments of a
population based on a specific
characteristics (e.g. gender, age-group,
districts, etc.)
definition of Representative sampling
sample’s
characteristic closely approximately to the
population
Sampling bias
systematic over- or
under-representation of some segment of
the population
what is probability (random) sampling. what are the advantages?
Everyone in the population has equal
opportunity (chance) for selection as a
subject
* Increases sample’s representativeness of the
population
* Decreases sampling error and sampling bias
* Results can be generalized to population
what is non probability sampling and its disadvantages?
Not every
element of the population has the
opportunity for selection in the sample
* May not have sampling frame or population
parameters may be unknown
* Non-random selection
* More likely to produce a biased sample
* Restricts generalization
* Quite often in medical and nursing research
list the 4 types of probability sampling methods
1) simple random sampling
2) stratified random sampling
3) systematic sampling
4) cluster (random) sampling
what is simple random sampling? what are the advantage and disadvantages?
What it is: Every individual in the population has an equal chance of being chosen.
How it works: Assign numbers to each individual, then use a random number generator or draw lots.
Example: You want to survey 100 employees in a company of 1,000. You assign numbers to all employees and randomly pick 100 using a computer.
advantage: easy to implement, less bias
disadvantage: must have a sampling frame
explain systematic sampling, advantages and disadvantages
What it is: Select individuals at regular intervals from a list.
How it works: Divide the population size by the desired sample size to get the interval (e.g., every 10th person).
Example: A school has 1,000 students, and you need 100 for a study. Starting at a random point, you pick every 10th student on the list.
Advantages
* Easier perform in the field
* Suitable for no good sampling
frame
* Disadvantages
* May have systematic bias (due to
the non-uniform distribution of
elements)
explain stratified sampling
What it is: Divide the population into subgroups (strata) based on a characteristic (e.g., age, gender) and sample from each group proportionally.
How it works: Ensure each subgroup is represented in the same proportion as in the population.
Example: In a population of 10,000 with 60% women and 40% men, a sample of 1,000 should include 600 women and 400 men.
Commonly used strata
* Personal characteristics: Gender, Age group
* Geographical: District, Province, Country
Advantages
* May produce a smaller error then simple random sampling
* Can reduce cost per observation
* Can measure parameters according to strata
* Disadvantages
* Sampling list and characteristics are necessary
explain cluster (random) sampling and the advantages + disadvantages
Cluster Sampling
What it is: Divide the population into clusters (e.g., geographic areas) and randomly select entire clusters.
How it works: Instead of sampling individuals, you randomly pick groups, then sample within those groups.
Example: A researcher studying schools in a district randomly selects 10 schools (clusters) and surveys all students within those schools.
Advantages
* Less costly
* A good sampling frame is difficult for elements but easy
for a collection of elements (e.g. primary school students)
* Disadvantages
* Systematic difference between clusters
what is non probability sampling?
Not every
element of the population has the
opportunity for selection in the sample
* May not have sampling frame or population
parameters may be unknown
* Non-random selection
* More likely to produce a biased sample
* Restricts generalization
* Quite often in medical and nursing research
List the 5 types of non probability sampling
1) convenience sampling
2) quota sampling
3)consecutive sampling
4)snowball sampling
5)purposive sampling
explain convenience sampling
What it is: Select individuals who are easiest to access or most readily available.
How it works: Choose participants because they are nearby, willing, or easy to contact.
Example: A researcher surveys people at a shopping mall because they are readily available.
- Advantage – Easy to get with low cost
- Disadvantage – Atypical sample may lead to
bias and be difficult to generalize to the population
explain quota sampling
What it is: Divide the population into subgroups and fill a quota for each group.
How it works: Decide the proportion of each subgroup needed and then select participants non-randomly within those subgroups.
Example: A researcher studying customer preferences ensures 60% of the sample is women and 40% is men, matching the population ratio.
Identifying the population strata and figure out the
proportion of each strata, draw a convenient sample
according to the percentages.
Identifying the population strata and figure out the
proportion of each strata, draw a convenient sample
according to the percentages.
explain consecutive sampling
every eligible participant within a defined population or time period is included in the study until the required sample size is reached. It is often considered a practical and inclusive method because it involves selecting participants consecutively as they meet the study criteria.
Best possible choice when there is rolling enrollment
- Advantage – Better than convenience sampling
especially for a long time frame - Disadvantage – May introduce serious bias if the time
frame is short or there are specific timeslots for subjects
what is snowball sampling?
What it is: Current participants help recruit more participants.
How it works: Begin with a small group and ask them to refer others who meet the criteria.
Example: A researcher studying a rare disease starts with one patient and asks them to refer others with the same condition.
Useful in recruiting subjects with specific criteria or
behavior that is socially unacceptable (e.g. drug
abuser, criminals)
- Advantage – Enable to recruit potential
subjects who are difficult to identify - Disadvantage – Referrals usually share
similar characteristics/features as the
first batch of subjects
what is purposive sampling?
What it is: Select participants based on specific characteristics or the researcher’s judgment.
How it works: Choose individuals who meet predefined criteria relevant to the research.
Example: To study the effects of a training program, only employees who attended the training are selected.
Advantage – Inclusion of subjects who are able to
provide detailed and relevant data/information to the
research questions.
* Disadvantage – Subjectivity of researcher’s decision
making, thus significantly threat to the validity of the
research conclusion.
what are the 4 methods of data collection?
1) self report
2) observation
3) biophysiological measures.
4) records and documents
what is self report?
Data gathered by questioning the sampled
subjects, usually called the respondents or participants
list the various forms of self reporting
- Questionnaire – Can include open or closed-end questions. dichotomous question = yes/ no
- scales
what is visual analog scales used for
to measure subjective
experience such as pain, fatigue, and dyspnea.
what are the possible bias for visual analog scales? 3
Social desirability bias
* Extreme response bias
* Acquiescence (Yea-saying) bias