SAMPLING METHODS

SPEAKER:- Shubhanshu Gupta

TEACHER I/C: Dr. B L Verma

DATE:- 05/08/2014

What exactly is a “sample”?

What exactly is a “sample”?

A subset of the population, selected by either “probability” or “non-

probability” methods. If you have a “probability sample” you simply know

the likelihood of any member of the population being included (not necessarily that it is “random.”

TARGET POPULATION

STUDY POPULATION

SAMPLE

Target vs. accessible populations

• The target population is the population a researcher would like to generalize to. Often this isn’t possible, so the accessible population is used. For example, a researcher might want to target all male elementary teachers in the India, but actually collects data from the male elementary teachers in Delhi.

Need for sampling

1. Complete enumeration may not be possible.

2. Resources: Lower cost, Lesser demand on personnel.

3. Speed: Faster results due to lesser coverage.

4. Reliable information: Due to small size - better trained personnel, more accurate methods, better supervision.

• To draw conclusions about population from sample, there are two major requirements for a sample.

– Firstly, the sample size should be large.– Secondly, the sample has to be selected appropriately

so that it is representative of the population. Sample should have all the characteristics of the population.

Disadvantages of sampling

1. Sampling entails an argument from the fraction to the whole. Validity depends on representativeness of the sample.

2. Fails to provide precise information in case of small segments containing few individuals.

3. Not necessary in studies where complete enumeration is needed.

4. May cause a feeling of discrimination among the subjects who are not included in the study.

Definitions

• Population: The target group to which the findings (of a study) would ultimately apply is called population1

Or• Population is the term statisticians use to describe a large set

or collection of items that have something in common2.

• Sample: is that part of the target population which is actually enquired upon or investigated1.

Or• Sample is a subset of population, selected in such a way that

it is representative of the larger population2

Definitions cont..

• Sampling unit: is the unit of selection

• Unit of study or element: is the subject on which information is obtained.

• Sampling frame: list of all sampling units in the target population is called a sampling frame.

• Sample size: the number of units or subjects sampled for inclusion in the study is called sample size.

• Sampling technique: Method of selecting sampling units from sampling frame

Definitions (cont.)

Sampling: is the process of selecting a small number of elements from a larger defined target group of elements such that the information gathered from the small group will allow judgments to be made about the larger groups.

conclusions based on the sample results may be attributed only to the population sampled*. .

SAMPLING PROCESSIdentifying and defining the target population

Describing the accessible population & ensuring sampling frame

Specifying the sampling unit

Specifying sampling selection methods

Determining the sample size

Specifying the sampling plan

Selecting a desired sample

Assumptions of quantitative sampling

We want to generalize to the population.

Random events are predictable.

Therefore…We can compare random events to our results.

Probability sampling is the best approach.

Assumptions of qualitative sampling

Social actors are not predictable like objects.

Randomized events are irrelevant to social life.

Probability sampling is expensive and inefficient.

Therefore…

Non-probability sampling is the best approach.

Target population

Sampling frame

Sample

Population you want to generalize results to

Population you have access to for your study

Study population

How can you get access to study population?

Study actually done on?

1.2.3…..

Types of sampling in quantitative researches

Probability samples

Non-probability

samples

Probability Techniques

Probability techniques

Simple Random Sampling

Systemic Sampling

Stratified Sampling

Disproportionate

Proportionate

Cluster Sampling Others

Non-probability Sampling

• Non probability sampling does not involve random selection• Accidental or Purposive

Non-probability techniques

Convenience Sampling

Judgemental Sampling Quota Sampling Snowball

Sampling

Conditions Favoring the Use of

Factors

Nonprobability sampling

Probability sampling

Nature of research

Exploratory

Conclusive

Relative magnitude of sampling and nonsampling errors

Nonsampling errors are larger

Sampling errors are larger

Variability in the population

Homogeneous (low)

Heterogeneous (high)

Statistical considerations

Unfavorable Favorable

Operational considerations Favorable Unfavorable

PROBABILITY SAMPLING TECHNIQUE

Features of the probability sampling

• It is a technique wherein the sample are gathered in a process that given all the individuals in the population equal chances of being selected.

• In this sampling technique, the researcher must guarantee that every individual has an equal opportunity for selection.

• The advantage of using a random sample is the absence of both systematic & sampling bias.

• The effect of this is a minimal or absent systematic bias, which is a difference between the results from the sample & those from the population.

Simple random sampling

• This is the most pure & basic probability sampling design.

• In this type of sampling design, every member of population has an equal chance of being selected as subject.

• The entire process of sampling is done in a single step, with each subject selected independently of the other members of the population

• There is need of two essential prerequisites to implement the simple random technique: population must be homogeneous & researcher must have list of the elements/members of the accessible population.

SRS with replacement (SRSWR):

In SRSWR the units selected in the earlier draws are replaced back in the population before the subsequent draws are made. Thus a unit has a chance of being included in the sample for more than once.SRS without replacement (SRSWOR) : Most common

In SRSWOR the units selected in the earlier draws aren’t replaced back in the population before the subsequent draws are made. Thus a unit has only one chance of being included in the sample.

The first step of the simple random sampling technique is to identify the accessible population & prepare a list of all the elements/members of the population. The list of the subjects in population is called as sampling frame & sample drawn from sampling frame by using following methods:

The lottery method

The use of table of random numbers

The use of computer

The lottery method…

It is most primitive & mechanical method.

Each member of the population is assigned a unique number.

Each number is placed in a bowl or hat & mixed thoroughly.

The blind-folded researcher then picks numbered tags from the hat.

All the individuals bearing the numbers picked by the researcher

are the subjects for the study.

Lottery method

Lottery method

Different random number table:

• Tipetts (1927) Random Number Table

• Fisher & Yates (1938)

• Kendall & Babington Smith`s (1939)

• Rand Corporation (1955) table of random numbers.

• C.R-Rao, Mitra & Mathai (1966) table of random numbers

Random number table

76 58 30 83 64

47 56 91 29 34

10 80 21 38 84

00 95 01 31 76

07 28 37 07 61

The use of table of random numbers… This is most commonly & accurately used method in simple random sampling.

Random table present several numbers in rows & columns.

Researcher initially prepare a numbered list of the members of the population, & then with a blindfold chooses a number from the random table.

The same procedure is continued until the desired number of the subject is achieved.

If repeatedly similar numbers are encountered, they are ignored & next numbers are considered until desired numbers of the subject are achieved.

The use of computer…Nowadays random tables may be generated from the computer , & subjects may be selected as described in the use of random table.

For populations with a small number of members, it is advisable to use the first method, but if the population has many members, a computer-aided random selection is preferred.Excel:enter the function =RND() on any blank cell

Merits and Demerits

Merits • Ease of assembling the

sample • Fair way of selecting a

sample• Require minimum

knowledge about the population in advance

• It unbiased probability method

• Free from sampling errors

Demerits• It requirement of a complete

& up-to-date list of all the members of the population.

• Does not make use of knowledge about a population which researchers may already have.

• Lots of procedure need to be done before sampling

• Expensive & time-consuming

Systematic Random Sampling

• It can be likened to an arithmetic progression, wherein the difference between any two consecutive numbers is the same.

• It involves the selection of every Kth case from list of group, such as every 10th person on a patient list or every 100th person from a phone directory.

• Systematic sampling is sometimes used to sample every Kth person entering a bookstore, or passing down the street or leaving a hospital & so forth

• Systematic sampling can be applied so that an essentially random sample is drawn.

If we had a list of subjects or sampling frame, the following procedure could be adopted. The desired sample size is established at some number (n) & the size of population must know or estimated (N).

Number of subjects in target population (N) K = N/n or K= Size of sample

For example, a researcher wants to choose about 100 subjects from a total target population of 500 people. Therefore, 500/100=5. Therefore, every 5th person will be selected.

If the ordering of the elements produces a cyclical pattern, systematic sampling may decrease the representativeness of the sample.

For example, there are 100,000 elements in the population and a sample of 1,000 is desired. In this case the sampling interval, i, is 100. A random number between 1 and 100 is selected. If, for example, this number is 23, the sample consists of elements 23, 123, 223, 323, 423, 523, and so on.

Systematic random sampling(contd.)

• For example, if there are 100 patients (N) in a hospital and to select a sample of 20 patients (n) by systematic random sampling procedure,

• Step 1: write the names of 100 patients in alphabetical order or their roll numbers one below the other.

• Step 2: sampling fraction: divide N by n to get the sampling fraction (k).In the example k=100/20 = 5.

• Step 3: randomly select any number between 1 to k i.e. between 1 to 5. Suppose the number we select is 4.

• Step 4: patient number 4 is selected in the sample. • Step 5: Thereafter every 4+k th patient is selected in the sample

until we reach the last one.

Systematic random sampling(contd.)

Merits and Demerits

Merits • Convenient & simple to

carry out.

• Distribution of sample is spread evenly over the entire given population.

• Less cumbersome, time-consuming, & cheaper

Demerits• If first subject is not randomly

selected, then it becomes a nonrandom sampling technique

• Sometimes this may result in biased sample.

• If sampling frame has nonrandomly, this sampling technique may not be appropriate to select a representative sample.

Systematic random sampling(contd.)

• Example:–District level household & facility survey

for Reproductive and child health – 1998-99, 2002-03, 2010-11.–Random blinded rechecking of slides under

RNTCP. Slides are drawn from the register by systematic random sampling.

Stratified Random Sampling

• This method is used for heterogeneous population.

• It is a probability sampling technique wherein the researcher divides the entire population into different homogeneous subgroups or strata, & then randomly selects the final subjects proportionally from the different strata.

• The strata are divided according selected traits of the population such as age, gender, religion, socio-economic status, diagnosis, education, geographical region, type of institution, type of care, type of registered nurses, nursing area specialization, site of care, etc.

Stratified Sampling

In proportionate stratified sampling, the size of the sample drawn from each stratum is proportionate to the relative size of that stratum in the total population.

In disproportionate stratified sampling, the size of the sample from each stratum is not proportionate to the relative size of that stratum and to the standard deviation of the distribution of the characteristic of interest among all the elements in that stratum.

Stratified random sampling(contd.)

• For example, if we draw a simple random sample from a population, a sample of 100 may contain – 10 to 15 from high socioeconomic group– 20 to 25 from middle socioeconomic group– 70 to 75 from low socioeconomic group

• To get adequately large representation for all the three socio economic structures, we can stratify on socioeconomic class and select simple random samples from each of the three strata.

POPULATION

LOW SOCIOECONOMIC

MIDDLE SOCIOECONOMIC

HIGH SOCIOECONOMIC

STRATIFIED SAMPLING

GROUP 1GROUP2GROUP 3

GROUP 4

Merits and Demerits

Merits • It representation of all group in a

population• For observing relation between

subgroup• • Observe smallest & most

inaccessible subgroups in population

• Higher statistical precision • Save lot of time, money, & effort

Demerits

• It require accurate information on the proportion of population in each stratum.

• Large population must available from which select sample

• Possibility of faulty classification

Cluster sampling

• The population is divided into subgroups (clusters) like families. A simple random sample is taken of the subgroups and then all members of the cluster selected are surveyed.

• Cluster sampling is used when the population is heterogeneous.

• Clusters are formed by grouping units on the basis of their geographical locations.

• Cluster sampling is a very useful method for the field epidemiological research and for health administrators.

Cluster sampling

Cluster sampling

Cluster 4

Cluster 5

Cluster 3

Cluster 2Cluster 1

Cluster sampling (contd.)

• A special form of cluster sampling called the “30 X 7 cluster sampling”, has been recommended by the WHO for field studies in assessing vaccination coverage.

• In this a list of all villages (clusters) for a given geographical area is made.

• 30 clusters are selected using Probability Proportional to Size (PPS).

• From each of the selected clusters, 7 subjects are randomly chosen.

• Thus a total sample of 30 x 7 = 210 subjects is chosen. • The advantage of cluster sampling is that sampling frame is not

required

CLUSTER SAMPLINGIt is sometimes called area sampling because this is usually applied when the population is large. In this technique, groups or clusters instead of individuals are randomly chosen.

• For each selected cluster, either all the elements are included in the sample (one-stage) or a sample of elements is drawn probabilistically (two-stage).

Merits and Demerits

Merits • It cheap, quick, & easy for

a large population.• Large population can be

studied, & require only list of the members.

• Investigators to use existing division such as district, village/town, etc.

• Same sample can be used again for study

Demerits • This technique is the

least representative of the population.

• Possibility of high sampling error

• This technique is not at all useful.

MULTI-STAGE SAMPLING

Refers to a sampling techniques which is carried out in various stages.

Population is regarded as made of a number of primary units each of which further composed of a number of secondary units.

Consists of sampling first stage units by some suitable method of sampling.

From among the selected first stage units, a sub- sample of secondary stage units is drawn by some suitable method of sampling which may be same as or different from the method used in selecting first stage unit.

Multistage random sampling

• In this method, the whole population is divided in first stage sampling units from which a random sample is selected.

• The selected first stage is then subdivided into second stage units from which another sample is selected.

• Third and fourth stage sampling is done in the same manner if necessary.

• Example:

– NFHS data is collected by multistage sampling.• Rural areas – 2 stage sampling – Villages from list by PPS,

Households from village• Urban areas – Wards (PPS) – CEB (PPS) – 30 households

from each CEB

• Combination of all the methods described above.

Involves selecting a sample in at least two stages.

e.g: i. Stage 1: Stratified Sampling Stage 2: Systematic Sampling

e.g: ii. Stage 1: Cluster Sampling Stage 2: Stratified Sampling

Stage 3: Simple Random Sampling

Multi-stage Sampling

Stratified Cluster sampling

Advantages:II stage units are necessary only for selected I stage units

Flexible & allows different selection procedure

Easier to administer

A large number of units can be sampled for a given cost.

.

Sequential Sampling

• This method of sample selection is slightly different from other methods.

• Here the sample size is not fixed. The investigator initially selects small sample & tries out to make inferences; if not able to draw results, he or she then adds more subjects until clear-cut inferences can be drawn.

Merits and Demerits

• Facilitates to conduct a study on best-possible smallest representative sample.

• Helping in ultimately finding the inferences of the study.

• With this sampling technique it is not possible to study a phenomenon which needs to be studied at one point of time.

• Requires repeated entries into the field to collect the sample.

NONPROBABILITY SAMPLING TECHNIQUE

Features of the nonprobability sampling

• It is a technique wherein samples are gathered in a process that does not give all the individual in the population equal chances of being selected.

• Most researchers are bound by time, money, & workforce, & because of these limitations, it is almost impossible to randomly sample the entire population & it is often necessary to employ another sampling technique, the nonprobability sampling technique.

• Subject in a nonprobability sample are usually selected on the basis of their accessibility or by the purposive personal judgment of the researcher

Uses of Non probability Sampling

• This type of sampling can be used when demonstrating that a particular trait exists in the population.

• It can also be used when researcher aims to do a qualitative, pilot , or exploratory study.

• It can be used when randomization is not possible like when the population is almost limitless.

• it can be used when the research does not aim to generate results that will be used to create generalizations.

• It is also useful when the researcher has limited budget, time, & workforce.

• This technique can also be used in an initial study (pilot study)

Types of the Nonprobability Sampling

Purposive/judgmental sampling Convenience/grab/availability sampling Consecutive samplingQuota sampling Snow ball sampling

Purposive/deliberate sampling• It is more commonly known as ‘judgmental’ or ‘authoritative sampling’.

• In this type of sampling, subjects are chosen to be part of the sample with a specific purpose in mind.

• In purposive sampling, the researcher believes that some subjects are fit for research compared to other individual. This is the reason why they are purposively chosen as subject.

• In this sampling technique, samples are chosen by choice not by chance, through a judgment made the researcher based on his or her knowledge about the population

• It is more commonly known as ‘judgmental’ or ‘authoritative sampling’.

• In this type of sampling, subjects are chosen to be part of the sample with a specific purpose in mind.

• In purposive sampling, the researcher believes that some subjects are fit for research compared to other individual. This is the reason why they are purposively chosen as subject.

• In this sampling technique, samples are chosen by choice not by chance, through a judgment made the researcher based on his or her knowledge about the population

For example, a researcher wants to study the lived experiences of post disaster depression among people living in earthquake affected areas of Gujarat.

In this case, a purposive sampling technique is used to select the subjects who were the victims of the earthquake disaster & have suffered post disaster depression living in earthquake-affected areas of Gujarat.

In this study, the researcher selected only those people who fulfill the criteria as well as particular subjects that are the typical & representative part of population as per the knowledge of the researcher.

Merits and Demerits

Merits • Simple to draw sample

& useful in explorative studies

• Save resources, require less fieldwork.

Demerits • Require considerable knowledge

about the population under study.

• It is not always reliable sample, as conscious biases may exist.

• Two main weakness of purposive sampling are with the authority & in the sampling process.

• It is usually biased since no randomization was used to obtained the sample.

Convenience/haphazard Sampling

• It is probably the most common of all sampling techniques because it is fast, inexpensive, easy, & the subject are readily available.

• It is a nonprobability sampling technique where subjects are selected because of their convenient accessibility & proximity to the researcher.

• The subjects are selected just because they are easiest to recruit for the study & the researcher did not consider selecting subjects that are representative of the entire population

• It is also known as an accidental sampling.

• Subjects are chosen simply because they are easy to recruit.

the process of including whoever happens to be available at the time…called “accidental” or “haphazard”

sampling

For example, if a researcher wants to conduct a study on the older people residing in Jhansi, & the researcher observes that he can meet several older people coming for morning walk in a park located near his residence in Jhansi, he can choose these people as his research subjects.

These subjects are readily accessible for the researcher & may help him to save time, money, & resources.(man on the streets)

Merits and Demerits

Merits • This technique is

considered easiest, cheapest, & least time consuming.

• This sampling technique may help in saving time, money, & resources.

Demerits • Sampling bias, & the

sample is not representative of the entire population.

• It does not provide the representative sample from the population of the study.

• Findings generated from these sampling cannot be generalized on the population.

Consecutive Sampling

• It is very similar to convenience sampling except that it seeks

to include all accessible subjects as part of the sample.

• This nonprobability sampling technique can be considered as

the best of all nonprobability samples because it include all

the subjects that are available, which makes the sample a

better representation of the entire population.

• It is also known as total enumerative sampling.

In this sampling technique, the investigator pick up all the available subjects who are meeting the preset inclusion & exclusion criteria.

This technique is generally used in small-sized populations.

For example, if a researcher wants to study the activity pattern of post kidney-transplant patient, he can selects all the post kidney transplant patients who meet the designed inclusion & exclusion criteria, & who are admitted in post-transplant ward during a specific time period.

Merits and Demerits

Merits • Little effort for sampling

• It is not expensive, not time consuming, & not workforce intensive.

• Ensures more representativeness of the selected sample.

Demerits • Researcher has not set plans

about the sample size & sampling schedule.

• It always does not guarantee the selection of representative sample.

• Results from this sampling technique cannot be used to create conclusions & interpretations pertaining to the entire population.

Quota Sampling

• It is nonprobability sampling technique wherein the researcher ensures equal or proportionate representation of subjects, depending on which trait is considered as the basis of the quota.

• The bases of the quota are usually age, gender, education, race, religion, & socio-economic status.

• For example, if the basis of the quota is college level & the research needs equal representation, with a sample size of 100, he must select 25 first-year students, another 25 second-year students, 25 third-year, & 25 fourth-year students.

Types of Quota Sampling

• Proportional quota sampling – representing the major characteristics of the population by sampling a proportional amount of each.

• Non-proportional quota sampling is a bit less restrictive. In this method, you specify the minimum number of sampled units you want in each category. Here, you're not concerned with having numbers that match the proportions in the population. Instead, you simply want to have enough to assure that you will be able to talk about even small groups in the population.

Quota sampling may be viewed as two-stage restricted judgmental sampling.

– The first stage consists of developing control categories, or quotas, of population elements. – to develop these quotas the researcher lists relevant control characteristics and determine the distribution of these characteristics in the target population. The relevant control characteristics (gender, age, race) are identified on the basis of judgment

– In the second stage, sample elements are selected based on convenience or judgment. Once the quota have been assigned, there is considerable freedom of selecting the element to be included in the sample. The only requirement is that the element selected fit the control characteristics.

Merits and Demerits

Merits • Economically cheap, as

there is no need to approach all the candidates.

• Suitable for studies where the fieldwork has to be carried out, like studies related to market & public opinion polls.

Demerits • It not represent all

population• In the process of sampling

these subgroups, other traits in the sample may be overrepresented.

• Not possible to estimate errors.

• Bias is possible, as investigator/interviewer can select persons known to him.

Snowball/networking Sampling

• It is a nonprobability sampling technique that is used by researchers to identify potential subjects in studies where subjects are hard to locate such as commercial sex workers, drug abusers, etc.

• For example, a researcher wants to conduct a study on the prevalence of HIV/AIDS among commercial sex workers.

• In this situation, snowball sampling is the best choice for such studies to select a sample.

• This type of sampling technique works like chain referral. Therefore it is also known as chain referral sampling.

After observing the initial subject, the researcher asks for assistance from the subject to help in identify people with a similar trait of interest

The process of snowball sampling is much like asking subjects to nominate another person with the same trait.

The researcher then observes the nominated subjects & continues in the same way until obtaining sufficient number of subjects.

Merits and Demerits

Merits • The chain referral process

allows the researcher to reach populations that are difficult to sample when using other sampling methods.

• The process is cheap, simple, & cost-efficient.

• Need little planning & lesser workforce

Demerits • Researcher has little

control over the sampling method.

• Representativeness of the sample is not guaranteed.

• Sampling bias is also a fear of researchers when using this sampling technique.

Errors in Sampling

• Non-Observation Errors– Sampling error: naturally occurs

– Coverage error: people sampled do not match the population of interest

– Underrepresentation

– Non-response: won’t or can’t participate

Errors of Observation

• Interview error- interaction between interviewer and person being surveyed

• Respondent error: respondents have difficult time answering the question

• Measurement error: inaccurate responses when person doesn’t understand question or poorly worded question

• Errors in data collection