Probability sampling methods and

Nonprobability sampling methds

Reporters
Melba Cua
Armando D. Dalisay Jr.
Objectives
May be able to differentiate between the probability and
nonprobability sampling method.

Enumerate and define the probability sampling methods.

 Provide examples for each methods.

A. Sampling Method
 it is the method of selecting a representative subset of the
population called sample.

 makes research more accurate and economical.

 it determines the generalizability of research findings.

Case 1
 You wish to study newspaper reading habits among the students of
your college. It’s not possible to include all the students in your study.
So, you draw a sample of the whole population – all the students of the
university.

 Suppose, from a total of 500 students of your college, we have selected

a sample of 50 students out of whether they read a newspaper or not?
To calculate the portion of students qualified to be part of the sample,
you have to divide sample size by population size; 50/500 = .10. This
reveals 10 percent of the population is to be studied.
Case 1 cont.
 One of the most asked questions is what is the best sample 100, 300, 500, 1000
or what?

 Seriously speaking, numbers are not as important as the representation of the

sample.

 A sample should be the representative of whole population.

 As given sample, after dividing population size by sample size, (500/50=10), we

found that each element of sample represents 10 students of the total population.
Probability Sampling
 this method of sampling gives the probability that our sample is
representative of a population.

 each sample has an equal probability of being chosen.

 a probability sample is one in which element of the population has a

known non-zero probability of selection.
Case 2
 There are 500 students in your college. You adopt a method in which
all the 500 students of your college have an equal chance to be
participants in your study, this is called probability sampling.

 In other words, to choose a sample, probability sampling uses

random sampling techniques.
Case 3
 If you had a population of 100 people, each person would have odds
of 1 out of 100 of being chosen.

 In this sampling method, there is an utmost probability of a

representative sample of the whole population.
Probability Sampling Methods
1. Simple Random Sampling
2. Stratified Random Sampling
3. Systematic Random Sampling
4. Cluster Sampling
5. Multi-stage Systematic Sampling
 Types of Sampling Methods
Samples

Non-Probability Probability Samples

Samples
Simple
Random Stratified
Convenience Quota
Cluster
Systematic
Purposive Snowball
1. Simple Random Sampling
 is a completely random method of selecting a sample in which each
element and each combination of elements in the population have an
equal probability of being selected as part of sample.

 best known probability sample.

 Even though it may not be considered as an ideal method of choosing

the sample, still result obtained through this method has high external
validity or generalizability as compared to some other method of
sample selection.
Techniques in Simple Random Sampling
1. Tossing a coin
2. Throwing a dice
3. Lottery method
4. Blindfolded method

 It can be conducted in two ways; with and without replacement.

Random Sampling can be conducted in two
ways

Sampling with Replacement

a certain element is selected and has a chance to be selected again
after the required variables are measured.

Sampling without Replacement

 an element once obtained cannot be selected again.
Case 4
 Let’s assume that you have to study the newspaper reading habits of
students of you college. The college has maintained a computerized
record of all the students currently enrolled (sampling frame).
 Now, suppose you have to draw a sample of 100 students from this
enrolment list. You have several options to draw the sample.
 You will have to write the names of all the 500 students of your
university on the tickets in a hat.
 Then, you will shake the hat again and pick another ticket. You will
repeat the method until you select the sample.
2. Systematic Random Sampling
 is an improvement over the simple random sampling.
 requires the complete information about the population.
 selecting one unit from the sampling frame and then calculations to
draw the following units are done on the basis of interval size.
 choosing the nth participant from the complete list.
 a combination of elements has different probabilities in systematic
random sampling.
 Systematic Samples
• Decide on sample size: n
• Divide population of N individuals into groups of
k individuals: k = N/n
• Randomly select one individual from the 1st group.
• Select every k-th individual thereafter.

N = 64
n=8
First Group
k=8
Case 5
 You choose every 5th student, roll no. wise in your class. After deciding
the sample size to be drawn, all you have to do is number the units in
population from 1 to N.
 Your college has 500 students and you have decided to draw a sample
of 50.
 The interval size, as calculated above in an example is equal to
(500/50) 10.
 Select a random number from 1 to 10.
 Suppose we have selected 7th unit in the list, and keep on adding 10 to
every new number to get all the elements.
Case 5 cont.
 Following the procedure, you will get a sequence of 7, 17, 27, 37…
 be careful to avoid periodicity, that is, an unrepresentative sample
because of the periodic nature of elements.
 Says TV shows that appear on certain day of the week.
 So if you were to sample TC shows on every 7th day, you would only
end up with TV shows from the same day of the week.
 Population must be listed in a random order and every element must
be chosen from the sequence framed.
3. Stratified Sampling
 is an improvement over systematic sampling.

 the population elements are divided into strata on the basis of some
characteristics and from each of these smaller homogeneous groups
draws at random a predetermined number of units.
Stratified random sampling can be two types
1. Proportionate Stratified Random Sampling
 size of the sample is proportionate to the size of the unit.

2. Disproportionate Stratified Random Sampling

 sample is not proportionate to the size of the unit.
 depends upon considerations involving personal judgments and convenience
 Stratified Samples
• Population divided into 2 or more groups according
to some common characteristic.
• Simple random sample selected from each.
• The two or more samples are combined into one.
Case 6
 You can divide the administration of your college into two
subgroups; teaching and non-teaching staff.
 To ensure adequate representation of each stratum (subgroup), the
sample is then drawn from each stratum randomly or systematically.
 Strata are divided keeping in mind that there must be heterogeneity
between the strata and homogeneity with each stratum.
 In case of stratified sampling, there is an increase in the accuracy of
the result if each stratum is more homogeneous within and
heterogeneous between each other.
Case 6 cont.
 For instance you need to draw a sample of “n” students from “N.”
 You will actually choose a sample of n1 + n2 + n3….equaling N from
mention subgroups N1, N2, N3…Nx.
 This way, you will be able to draw a more representative sample of
students in your college.
 This method is cardinal when a need to over-sample particular
subgroup is required.
4. Cluster Sampling
 population is divided into clusters and then a sample is selected from the
clusters randomly.

 one of the efficient methods of random sampling.

 there should be heterogeneity within the clusters and homogeneity

between the clusters.

 the more homogeneity among the clusters, lesser will be the margin of
error or vice versa.
Cluster sampling cont.
 the method is mostly feasible in case of diverse population spread
over different areas.

 not possible in case of random sampling, the participants with

different demographics are selected randomly from these areas.
 Cluster Samples
• Population divided into several “clusters”,
each representative of the population.
• Simple random sample selected from each.
• The samples are combined into one.

Population
divided into
4 clusters.
Case 7
 Suppose, you want to study the average woman’s height in India.

 It is not possible to get a list of everyone.

 In such case, you will convert the areas into clusters and draw a
sample randomly from those clusters.
5. Multi-Stage Sampling
 the population is divided into groups at various levels.

 a group within a group and so on.

 the sample is finally drawn from the smallest group among all the
groups.
Case 8
 Suppose you want to study the coverage of the Indian Express
newspaper on gender issues for ten years from 2000 to 2010.
 You may break the period giving a five year gap and select years
2000, 2005 and 2010 for the study.
 Then you may further select three months – for example January,
June and December – of the aforementioned years for the study.
 You may further reduce the number of issues to be studied and
select only first weeks of all the three months of the selected years.
Case 8 cont.
 You may further construct an odd-numbered week or even-
numbered week and reduce your sample size.

 Finally, you may select an odd-numbered week in January and even-

numbered in June and odd-numbered week in December.

 You may follow this sequence and select 63 issues of the newspaper
for the study.
B. Non-Probability Sampling
 uses non-randomized methods to draw the sample.
 mostly involves judgment.
 participants are selected because they are easy to access.
(classmates and friends)
 even though in certain cases, non-probability sampling is a useful
and convenient method of selecting sample, the method is
appropriate and the only method available in certain cases.
B. Non-Probability Sampling cont.
 one of the major shortcomings of the non-probability sampling is
that the findings establish lacks generalizeability.
 even though findings obtained through this method apply mostly to
the group studied, it may be wrong to extend these findings beyond
that particular sample.
 we can study particular phenomena to generate valuable insights.
 used to study existing theoretical insights or developing new ones.
 considered less expensive, less complicated and easy to apply.
Non-probability methods
1. Convenience Sampling
2. Purposive Sampling
3. Quota Sampling
4. Snowball Sampling
1. Convenience Sampling
 researchers prefer participants as per their own convenience.
 researchers the closest live persons as respondents.
 subjects who are readily accessible or available to the researcher are
selected.
 whoever meets the researcher qualifies to be part of your sample.
 eg. People passing in the streets gets the questionnaire from the
researcher to be filled in.
2. Purposive Sampling
 researchers chooses participants as per his/her own judgment,
keeping back in mind the purpose of the study.
 it uses judgment of an expert in selecting cases or it selects cases
with a specific purpose in mind.
 used in exploratory research or field research.
 the researcher hardly knows whether the cases selected do
represent the population or not.
 most of the sampling method may be considered purposive in
nature.
Case 9
 For studying attitude toward any national issue, a sample of
journalists, teachers and legislators may be selected for the study.

 They qualify to be part of purposive sampling as they can more

reasonably be expected to represent the correct attitude than other
class of people.
3. Quota Sampling
 pre-plan the number of participants in specified categories. (100
literates, 100 illiterates)

 you select a sample from according to some fixed data.

 the allot shares to different groups.

Types of Quota Sampling
1. Uncontrolled Quota Sampling
 the researcher selects sample as per her own convenience.

2. Controlled Quota Sampling

 some restrictions are imposed to limit the researcher’s choice.
4. Snowball Sampling
 also called “chain referral sampling”
 sample is actually collected in various stages.
 basically socio-metric in nature.
 this method is appropriate when the members of a special
population are difficult to locate for example homeless people.
 it begins by the collection of data from one or more contracts usually
known to person collecting the data.
4. Snowball Sampling cont.
 At the end of data collection process, the data collector ask the
respondent to provide contact information for other potential
respondents.
 these potential respondents are contacted, interviewed and further
asked to provide more contacts.
 this process goes on until the purpose of the researcher is achieved.
 most useful when there are very few methods to secure a list of the
population or when the population is unknowable.
 Types of Survey Errors
•Coverage Error Excluded from
selection.

Follow up on non
•Non Response Error responses.

Chance differences from

•Sampling Error sample to sample.

•Measurement Error Bad Question!

Reference
 https://www.researchgate.net/publication/319066480