Sampling (in Research)

Contents
1. Definitions -------------------------------------------------------------------------------------------1
1.1. Sample
1.2. Sampling
1.3. Basic Terms and Concepts
2. Why Samplingis done?-------------------------------------------------------------------------3
3. Types of population for sampling-------------------------------------------------------- 4
4. Characteristics of good sampling-------------------------------------------------------- 5
5. Sampling Process---------------------------------------------------------------------------- 6
6. Sampling Methods/Techniques----------------------------------------------------------- 8
6.1. Probability Sampling -------------------------------------------------------------------- 8
6.1.1. Simple Random------------------------------------------------------------------ 9
6.1.2. Systematic Random------------------------------------------------------------- 10
6.1.3. Cluster/Area Random----------------------------------------------------------- 11
6.1.4. Stratified Random--------------------------------------------------------------- 12
6.2. Non-Probability Sampling--------------------------------------------------------------13
6.2.1. Accidental Sampling------------------------------------------------------------ 13
6.2.2. Quota Sampling------------------------------------------------------------------ 13
6.2.3. Snowball Sampling-------------------------------------------------------------- 14
6.2.4. Judgmental Sampling----------------------------------------------------------- 15
6.3. Strengths and Weaknesses------------------------------------------------------------- 16
7. Sample Size----------------------------------------------------------------------------------- 17
8. Sampling Error------------------------------------------------------------------------------ 19
9. Confidence Interval & Confidence Level----------------------------------------------- 20
10. Conclusion------------------------------------------------------------------------------------ 21
11. References------------------------------------------------------------------------------------ 22

SAMPLING
1. Definitions

1.1.SAMPLE


A selection taken from a larger group (the "population") so that you can examine it to find out something about the larger group. (mathisfun.com)

1.2.SAMPLING


The process of obtaining information from a sample of a larger group (population).



To take a sample or samples of (something) for analysis. (Oxford Dictionaries)



The process of selecting a number of individuals for a study in such a way that the individuals represent the larger group from which they were selected.

1.3.BASIC TERMS AND CONCEPTS
a) Universe - the theoretical collection of all elements that apply to a particular survey.
E.g., if one is surveying librarians, the study universe will include all librarians, regardless of type and location. Universe is not frequently used today; it is often used synonymously with “population” and is essentially a useless term.
b) Population - the theoretical collection of specified elements as defined for a given survey, defined by time and space.E.g., Pakistan Academic Librarianswould be part of the universe of librarians and could represent the population for a survey study. The population is the aggregation of units to which one wishes to generalize the results of a research study.

c) Populationstratum - a subdivision of a population based on one or more specifications/characteristics. E.g., a stratum of the population of all Pakistan
Academic Librarians could be Pakistan academic librarians of libraries with a collection of at least 50,000 volumes or with a budget of a certain size.

1

d) Ele ment - an individual member or unit of a population. E.g., each academic librarian would be an element of the population of academic librarians. The total number of elements of a population is usually designated by „N‟.
e) Census - a count or survey of all the elements of a population, and the determination of the distribution of their characteristics. E.g., Academic Librarians. A complete census is usually not possible, or at least is impractical and unnecessary.
f) Sample - a selection of elements from the total population to be studied.
g) Samplingframe - the actual list of elements from which the sample, or some part of the sample, is selected. It is often used interchangeably with “population list.”
h) Case - an individual unit/element of the sample. The total number of cases in a sample is usually designated by lower-case „n‟.

Diagrammatic explanations of basic te rms
2

SAMPLING
2. Why sampling is done?
Sampling is donefor following reasons:
 When getting information about a large populations
 Less costly
 Less field time consumed
 Gain more accuracy, i.e. can do a better job of data collection when it‟s impossible to study the whole population.
It is not possible to collect data for research purpose from large population, so sampling is done. From sample, data is collected and the research findings are applied to the whole population. This method may not be suitable for scientific research, as in scientific research every element or subject of study is important.
It is generally more economical in time, effort and money to use sampling. It remains the only way when the population contains infinite elements.

3

3. Types of population for sampling
There are two types of population:
a) Homogeneous
b) Heterogeneous

a) Homogeneous
If all members of a population were identical, the population is considered to be homogeneous. This means, the characteristics of any one individual in the population would be the same as the characteristics of any other individual (little or no variation among individuals).
For example,


First year MLIS students of University of
Punjab.



Primary school teachers of Islamabad Model College for Girls (IMCG).

b) Heterogeneous
When individual members of a population are different from each other, the population is considered to be heterogeneous (having significant variation among individuals).In order to describe a heterogeneous population, observations of multiple individuals are needed to account for all possible characteristics that may exist.
For example


Academic librarian such as university librarians, college librarians & school librarians; here librarians are of different academic environment, so, these are heterogeneous population.



Doctors having different specialties.
4

4. Characteristics of good sampling
Following are the characteristics of a good sampling / sample design (blog.reseapro.com):
1. Sample design should be a representative sample: A researcher selects a relatively small number for a sample from an entire population. This sample needs to closely match all the characteristics of the entire population. If the sample used in an experiment is a representative sample then it will help generalize the results from a small group to large population being studied.

2. Sample design should have small sampling error: Sampling error is the error caused by taking a small sample instead of the whole population for study. Sampling error refers to the discrepancy that may result from judging all on the basis of a small number.Sampling error is reduced by selecting a large sample and by using efficient sample design and estimation strategies.

3. Sample design should be economically viable: Studies have a limited budget called the research budget. The sampling should be done in such a way that it is within the research budget and not too expensive to be replicated.
4. Sample design should have marginal systematic bias: Systematic bias results from errors in the sampling procedures which cannot be reduced or eliminated by increasing the sample size. The best bet for researchers is to detect the causes and correct them.
5. Results obtained from the sample should be generalized and applicable to the whole population: The sampling design should be created keeping in mind that samples covers the whole population of the study and is not limited to a part.

5

5. Sampling Process

Sampling process includes five steps
1. Define the target population
2. Determine the sample frame
3. Select a sample technique
4. Determine sample size
5. Executing the sampling process

First of all the population is defined for which research is to be conducted to gain purposeful results. The sample frame (or population list) is picked from the targeted population i.e. the actual list of elements from which the sample, or some part of the sample, is selected.
The sampling method outlines the way in which the sample elements are to be selected. The choice of the sampling method is influenced by the objectives of the research, availability of financial resources, time constraints, and the nature of the problem to be investigated. All sampling methods can be grouped under two distinct heads, that is, probability and nonprobability sampling.
Sample size is how many elements are needed to include in the sample. It depends on the nature of the research and the type of data required to be collect.
The final step in the sampling process is the actual selection of the sample elements. This requires a substantial amount of office and fieldwork, particularly if personal interviews are involved. 6

Sampling Process- Flow Chart

7

6. Sampling Methods/Techniques

There are two types of sampling techniques.
 Probability sampling
 Non-probability sampling

6.1.PROBABILITY SAMPLING:
This method utilizes some form of random selection. A probability sampling method is any method of sampling that utilizes some form of random selection. In order to have a random selection method, researcher must set up some process or procedure that assures that the different units in the population have equal probabilities of being chosen.
Humans have long practiced various forms of random selection, such as picking a name out of a hat, or choosing the short straw. These days, computers are used as the mechanism for generating random numbers as the basis for random selection.
(socialresearchmethods.net)

Types of Probability Sampling
Types of Probability Sampling are of following types:


Simple Random



Systematic Random



Cluster/Area Random



Stratified Random

8

6.1.1. SIMPLE RANDOM SAMPLING
Simple random sampling is the basic sampling method of survey research. The technique of simple random sampling gives each element in the population an equal chance of being included in the sample. It also makes the selection of every possible combination of elements equally likely. In other words, if one had a population or sampling frame of 500 elements, in drawing a simple random sample of that population one should be as likely to include elements 1 and 3 as 2 and 4, or 1 and 2, and so on.

A sampling procedure in which every element in the population has a known and equal chance of being selected as a subject (e.g., drawing names out of a hat).

For example, suppose a voting area have, 1,000 votes and assume that the researchers want to select 100 of them for an opinion poll. The researchers might put all their names in a box and then pull 100 names out. Now this way each voter will have an equal chance of being selected.

9

6.1.2. SYSTEMATIC SAMPLING
If a sample size of n is desired from a population containing Nelements, we might sample one element for sampling interval N/n.
[N= population size; n=sample size]

Here are the steps that should be followed in order to achieve a systematic random sample
(socialresearchmethods.net):


number the units in the population from 1 to N



decide on the n (sample size) that is required



k = N/n = the interval size



randomly select an integer between 1 to k








N = 100
Want n = 20
N/n = 5
Select a random number from 1-5: choose 4
 Start with #4 and take every 5th unit

then take every kthunit

For example,let 's assume that we have a population that only has N=100 people in it and that you want to take a sample of n=20.
To use systematic sampling, the population must be listed in a random order. The interval size, k, is equal to N/n = 100/20 = 5.
Now, select a random integer from 1 to 5. Suppose that you chose 4.
Now, to select the sample, start with the 4th unit in the list and take every k-th unit (every 5th, because k=5).
You would be sampling units 4, 9, 14, 19, and so on to 100 and you would wind up with 20 units in your sample.

10

6.1.3. CLUSTER OR AREA RANDOM SAMPLING
In social science research, it is not unusual to encounter situations where the populations cannot be listed easily for sampling purposes. Examples include the populations of countries and states, all college students within the Pakistan, and so on. When it is impossible or impractical to compile an exhaustive list of the elements of a total population, cluster sampling may be used effectively. Steps involved in this sampling are:
1. the population is divided into clusters
(usually along geographic boundaries)
2. then choose clusters randomly (simple random, stratified, etc.)
3. chose sample frame in the selected clusters 4. take all elements from each cluster.

For example, while a list of a city‟s residents may not exist, people do live on d iscrete blocks.
Therefore, one could draw a sample of city blocks, compile lists of persons residing on those blocks, and then sample the people living on each block.

11

6.1.4. STRATIFIED SAMPLING
In selecting a stratified random sample, one must first divide all of the population elements into groups or categories and then draw independent random samples from each group or stratum. This technique represents a modification of simple and systematic random sampling in that it reduces the number of cases needed to achieve a given degree of accuracy or representativeness. The strata should be defined in such a way that each element appears in only one stratum. Different sampling methods may be used for different strata. For example, a simple random sample may be drawn from one stratum and a systematic sample from another. Population is divided on the basis of characteristic of interest in the population e.g., male and female may have different characteristics.

12

6.2.NON-PROBABILITY SAMPLING:


Itdoes not involve random selection.



Focus on volunteers, easily available units, or those that just happen to be present when the research is done.

Types of Non-Probability Sampling
Non-probability Sampling is of following types:


Accidental Sampling



Quota Sampling



Snowball Sampling



Judgmental Sampling

6.2.1. ACCINEDTAL SAMPLING
No system of selection is followed but only those whom the researcher or interviewer meets by chance are included in the sample. The process includes picking out people in the most convenient and fastest way to immediately get their reactions to a certain hot and controversial issue. For example, if one wished to conduct an academic library user study, one might elect to survey library patrons as they entered or exited the library, on a
“first-come, first-served” basis.Also known as convenience and availability sampling.

6.2.2. QUOTA SAMPLING
A type of nonprobability sample that improves somewhat on the simple accidental sample is the quota sample. Quota sampling is the same as accidental sampling except that it takes steps to ensure that the significant, diverse elements of the population are included. The quota sample method also attempts to ensure that the different elements are included in the sample in the proportions in which they occur in the population.
13

When specified number of persons of certain types are included in the sample then judgment is used to select the elements 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.
Quota sampling is often used for public opinion surveys.

6.2.3. SNOWBALL SAMPLING
Selecting participants by finding one or two participants and then asking them to refer you to others. For example, friends of friends or meeting a jobless person, interviewing that person, and then asking him/her to introduce you to other jobless persons he/she knows.
Used to sample from low incidence or rare populations.
It is an appropriate method to use when members of the population are difficult to identify and locate, such as migrants and homeless individuals. The researcher contacts members of the population who can be identified and located and then asks these individuals to provide information to identify and locate other members of the population to participate in the research.
This type of sampling is cumulative, hence the name, snowball sampling. This type of nonprobability sampling is used in exploratory research since the technique can result in
“samples with questionable representativeness.” It is commonly used in qualitative research.

14

6.2.4. JUDGMENTAL SAMPLING
The researcher chooses the sample based on who they think would be appropriate for the study.
This is used primarily when there is a limited number of people that have expertise in the area being researched.
The researcher selects units to be sampled based on their knowledge and professional judgment. For example, in designing a survey of the directors of large university libraries that are in the process of developing electronic reference services, one may decide that the easiest way of obtaining a sample of such libraries would be to select libraries known to the researcher to be engaged in such activities.
The researcher would be making the assumption that such a sample would be reasonably typical of all university libraries involved in developing electronic reference services. Unfortunately, such an assumption may not be justified. There is no assurance that a judgmental sample is actually representative of the total population. Any sampling method not utilizing random selection is overly susceptible to bias.
It is also known as purposive sampling and authoritativesampling.

15

6.3.Strengths and Weaknesses of Sampling Methods

16

7. Sample Size
Sample size means “How large should my sample be in order for it to be representative”?Larger samples are not necessarily better – how representative a sample it depends on the sampling technique used and the size of the population.
Determining sample size is dependent of how much error you are prepared to accept in your sample. The general rule of thumb for the size of the sample is, quite simply, the larger the better. Probability samples of less than 100 are not likely to be very representative of the population. Yet there is no point in utilizing a sample that is larger than necessary; doing so unnecessarily increases the time and money needed for a study.
Krejcie and Morgan developed a table of sample sizes for given population sizes. This table is presented here but, it should keep in mind that, a variety of factors can influence desirable sample size. A table of sample sizes may represent a rather simplistic, and quite possibly conservative, method for ascertaining a sample size.

17

18

8. Sampling Error

Sampling error is an error in a statistical analysis arising from the unrepresentativeness of the sample taken.The larger the sample size the more likely error in the sample will decrease. But, beyond a certain point increasing sample size does not provide large reductions in sampling error.
The use of a sample relative to an entire population is often necessary for practical and/or monetary reasons. Although there are likely to be some differences between sample analysis results and population analysis results, the degree to which these can differ is not expected to be substantial.

Methods of reducing sampling error include increasing the sample size and ensuring that the sample adequately represents the entire population.

19

9. Confidence Interval& Confidential Level

9.1. CONFIDENCE INTERVAL
The confidence interval (also called margin of error) is the plus-or- minus figure usually reported in newspaper or television opinion poll results. For example, if you use a confidence interval of 4 and 47% percent of your sample picks an answer you can be
"sure" that if you had asked the question of the entire relevant population between 43%
(47-4) and 51% (47+4) would have picked that answer.

9.2. CONFIDENCE LEVEL
The confidence level tells you how sure you can be. It is expressed as a percentage and represents how often the true percentage of the population who would pick an answer lies within the confidence interval. The 95% confidence level means you can be 95% certain; the 99% confidence level means you can be 99% certain. Most researchers use the 95% confidence level.
When you put the confidence level and the confidence interval together, you can say that you are 95% sure that the true percentage of the population is between 43% and 51%.
The wider the confidence interval you are willing to accept, the more certain you can be that the whole population answers would be within that range.

20

10. CONCLUSION
 Sampling procedures have always been widely applied in libraries because the full count of some data was impossible or too costly. The most common and one of the best, techniques for selecting a representative sample is simple random sampling.Depending on certain characteristics of the population, or on the purpose of the research, other probability techniques may be preferable in a given situation.There may even be occasions where non-probability sampling is preferable to probability sampling.  Basic characteristics of a sample design should…..
1. … be a representative sample
2. … have small sampling error
3. … be economically viable
4. … have marginal systematic bias
5. Results obtained from the sample should be generalized and applicable to the whole universe.

21

11. References
Creswell , John W. (2009). Research Design: Qualitative, Quantitative, and Mixed Methods
Approaches (3rd ed.). Los Angeles: SAGE Publications. http://marketresearch.about.com/od/market.research.surveys/a/Surveys-ResearchConfidence-Intervals.htm, retrieved on 23th Feb., 2014. http://blog.reseapro.com/2012/12/characteristics-of-a-good-sample-design/ , retrieved on 25th
Feb., 2014. http://blog.reseapro.com/2012/12/characteristics-of-a-good-sample-design/, retrieved on 25th
Feb., 2014. http://www.investopedia.com/terms/s/samplingerror.asp, retrieved on 25th Feb., 2014. http://www.mathsisfun.com/definitions/sample.html, retrieved on 25th Feb., 2014. http://www.oxforddictionaries.com/definition/english/sample, retrieved on 24th Feb., 2014. http://www.socialresearchmethods.net/kb/sampprob.php, retrieved on 23th Feb., 2014. http://www.socialresearchmethods.net/kb/sampprob.php, retrieved on 24th Feb., 2014.
Powell, R. R. (2010). Basic research methods for librarians (5 th ed.), California: Greenwood
Publishing Group.

22

References: Creswell , John W. (2009). Research Design: Qualitative, Quantitative, and Mixed Methods Approaches (3rd ed.) http://marketresearch.about.com/od/market.research.surveys/a/Surveys-ResearchConfidence-Intervals.htm, retrieved on 23th Feb., 2014. http://blog.reseapro.com/2012/12/characteristics-of-a-good-sample-design/ , retrieved on 25th Feb., 2014. http://blog.reseapro.com/2012/12/characteristics-of-a-good-sample-design/, retrieved on 25th Feb., 2014. http://www.investopedia.com/terms/s/samplingerror.asp, retrieved on 25th Feb., 2014. http://www.mathsisfun.com/definitions/sample.html, retrieved on 25th Feb., 2014. http://www.oxforddictionaries.com/definition/english/sample, retrieved on 24th Feb., 2014. http://www.socialresearchmethods.net/kb/sampprob.php, retrieved on 23th Feb., 2014. http://www.socialresearchmethods.net/kb/sampprob.php, retrieved on 24th Feb., 2014. Powell, R. R. (2010). Basic research methods for librarians (5 th ed.), California: Greenwood Publishing Group.