Transcript Sample

Basic concepts
Population: Is the entire aggregation of
cases that meet a designated set of criteria.
Examples:
1. All the women in Gaza strip who gave birth to a live
baby during the past decay.
2. All the women older than age 60 whom are under
psychological care.
3. All the children in Gaza strip with cystic fibrosis.
Population may be human subjects and might consist of
hospital records, all of the blood samples taken from
clients
Basic concepts
Accessible population:
Is the population of subjects available for
particular study.
"it is the aggregate of cases that conform to the
designated criteria and that are accessible to
the research as a pool of subjects of a study”.
The sample is obtained from the accessible
population, and findings are generalized first
to the accessible population and then, to the
target population.
Basic concepts
The target population:
Is the total group of subjects about whom the
investigator is interested and whom the results
could be reasonably generalized.
Basic concepts
The target population:
Example1: all RNs currently employed in the Gaza
Strip is the target population, but the more
modest accessible population is RNs working in
Gaza city.
Example2: A target population might consist of
all diabetic people in the Gaza Strip, but the
accessible population might consist of all diabetic
people who are members of a UNRWA clinic.
Sampling
• Sampling - refers to process of selecting a
portion of the population to represent the
entire population
• A sample consists of a subset of the units
that compose the population.
Population
Sample
Sampling
• Sampling determines who will be participants
in the study.
Aim
• A representative sample
– A sample which accurately reflects its population
• Avoiding bias
Why Use A Sample?
• Ideally the whole population should be used in a
study.
• Why would this be impractical in most studies?
• When would it be feasible to use the whole
population?
Representative Sample
• It is that sample whose key characteristics
are highly similar to those in the population
from it is drawn
• It is important that the sample not be biased.
• A representative sample is a sample which is
a true cross-section of the population you are
measuring.
How Do We Generalize?
Model I: Sampling
Population
Sample
draw
sample
draw
sample
How Do We Generalize?
Model I: Sampling
generalize
back
generalize
back
Population
Sample
Generalization
• If the sample is representative of the population
then it is possible to generalize the findings
from the study.
• If you can generalize you can say that the
results hold true not only for the sample that
you studied but the entire population from
which the sample was derived.
Basic terminology
• Population - the entire group of objects about which
information is wanted
• Target Population - the group that is the focus of your
research
• Accessible Population - members of the population
that you can reach
• Unit - any individual member of the population
• Sample - a part or subset of the population used to
gain information about the whole
• Sampling frame - the list of units from which the
sample is chosen
• Variable - a characteristic of a unit, to be measured
for those units in the sample
General population
Target Population
Accessible population.
Sample
Sample Statistic
Step 1: Identify the
Population
• The units of analysis about whom or which
you want to know
– Define the population concretely
• Example
– All registered staff who were working at
Shifa Hospital at the time of the study.
2. Specify the eligibility
criteria
• Inclusion criteria
– Registered staff who were working at Shifa
Hospital at the time of the study.
• Exclusion criteria
– Not formally staff as (pocket money) or staff who
were in maternity leave.
– Registered staff who moved outside Gaza for long
period such as vacation, education, and training
purposes.
3. Specify the Sampling plan
Once the accessible population has been
identified, you must decide:
1- The method of drawing the sample.
2- How large it will be?
4- Recruit the sample
• Institutional or Agency permission.
• Try to know the subjects cooperation.
Probability (Random) Sampling
• Every element in the population has a
known chance of being selected.
• No subject can be selected more than once
in a single sample.
• There are four major types of probability
sampling:
–
–
–
–
Simple Random Sampling.
Systematic Random Sampling.
Stratified Random Sampling.
Cluster Sampling.
How to choose
The nature of the
research problem
Money
Availability of a
sampling frame
Desired level of
accuracy
Data collection method
Sampling Strategies--Decision Flow
Study Population
Entire Population
Sample
“100% Sample”
or single case study?
Probability (Random)
Sample
Simple
Random
Sample
Systematic
Random
Sample
Stratified
Random
Sample
Determine sample
size
Cluster
Sampling
Quota
Sample
Non-probability
Sample
Purposive
Sample
Snowball
Sample
Convenience
Sample
Simple random sampling
• Is the most basic probability sampling design, because
the more complex probability sampling design
incorporate features of simple random sampling.
• Obtain a complete sampling frame
• Give each case a unique number starting with one
• Decide on the required sample size
• Select that many numbers from a table of random
numbers
• Select the cases which correspond to the randomly
chosen numbers
Simple random sampling
– Advantages
• High probability of achieving a representative sample
• Meets assumptions of many statistical procedures.
• Easy to analyze data and computer errors.
– Disadvantages
• Identification of all members of the population can be
difficult
• Contacting all members of the sample can be difficult
• Simple random is a time consuming chores especially if the
population is large.
• Expensive.
Systematic random sampling
• Involves taking the list of elements and choosing every
n/th element on the list.
• Sample interval
– divide the population size by the desired sample size
K= N/n
– e.g sample interval = 40,000/200 means that we select
one person for every 200 in the population
• The sample interval is the standard distance between the
elements chosen for the sample.
• The first element should be selected randomly
Systematic random sampling
– Advantage
• very easily done
– Disadvantages
• Some members of the population don’t have an
equal chance of being included.
If every 10th nurse listed in nursing personnel list
were a head nurse and a sampling interval was 10,
then head nurses would either always or never be
included in the sample.
Stratified random sampling
• The elements are divided into two or more strata or
subgroups
• The aim of stratification is to obtain a greater degree of
representativeness
• The population is subdivided into homogenous subsets,
e.g. age, gender, occupation …
• Proportional stratified sampling: e.g. 10% of black
students, 10% of Hispanic and 80% white students, then
the proportional stratified sample of 100 students will be
10, 5, 85 from the respective sub-population.
• Non-proportional stratified sampling (weighing): 20% +
20%+60%
stratified random sampling
– Advantage
• representation of subgroups in the sample
– Disadvantages
• Identifying members of all subgroups can be
difficult
• Require more labor and effort
Cluster sampling
• Involves drawing several different samples
– draw a sample of areas
– start with large areas then progressively sample
smaller areas within the larger
• Divide city into districts - select Simple Random
Selection (SRS) sample of districts
• Divide sample of districts into blocks - select SRS
sample of blocks
• Draw list of households in each block - select SRS
sample of households
Cluster sampling example
Population: all clinics in the district provided MCH services
One begins with the largest, most inclusive units (such as
governorates; moving on to less inclusive units as cities then
MCH clinics and then to the most basic units, e.g. pregnant
women.
1
3
5
9
3
2
7
5
4
6
10
7
8
10
Sample: a random sample of
clinics.
Cluster Random Sampling
– Advantages
• Very useful when populations are large and spread
over a large geographic region
• Convenient and practical
– Disadvantages
• Representation is likely to become an issue
• Assumptions of some statistical procedures can be
violated
Random Samples
• Advantages
– Ability to generalise from sample to population using
statistical techniques
• Inferential statistics
– High probability that sample generally representative
of the population on variables of interest
Nonprobability sampling
• In this method of sampling the researcher
purposively picks the elements that are
information rich.
• This is used for interpretive studies.
Under what circumstances would you use this
method?
• Depends on the population
• Problem and aims of the research
• Existence of sampling frame
Methods of Nonprobability Sampling
Quota sampling:
A form of non-probability sampling
It is one in which the researcher identifies "homogenous"
strata of the population and determine the proportion of
elements needed from the various segment of the
population
Purposive sampling "judgmental":
When the researcher attempts to ensure that specific
elements are included in the sample
This approach employs a high degree of selectivity
regarding the necessary characteristics of the desired
sample
Methods of Nonprobability Sampling
Snowball: initial participants lead to other participants. is
another type of convenience sampling. This approach is
sometimes used when specific traits are needed but difficult to
be identified by ordinary means. Suppose that researcher is
interested in studying mothers who had stopped breast feeding
their infants within one month of being released from hospital
Accidental or convenience : Involves the use of
convenient, or available, elements in the sample. It is
considered a poor approach to sampling because it provides
little opportunity to control for biases.
– In convenience sampling, subjects are included in the study
because they happened to be in the right place at the right
time.
Sample Size
• There is no simple formula that indicate how large a
sample is needed in a given study
• Use the largest sample size possible; the larger the
sample, the more representative of the population it
is likely to be
• The larger the sample, the smaller the sample error.
The size of the sample depends on three general items:
• The research approach being used.
• The homogeneity, or similarity, among the different
elements.
• The resources available to you. What is practical?
Sampling error
• Refers to differences between population
values, e.g. average age of population and
the sample value, such as the average age of
the sample
• A margin of error of 5% means that the
actual findings could vary in either direction
by as much as 5%.
Conclusion
• The purpose of sampling is to select a set of
elements from the population in such a way
that what we learn about the sample can be
generalised to the population from which it
was selected
• The sampling method used determines the
generalizability of findings
Random samples
Non-random sample